Devtu Fix Tool

Fix ToolUniverse Tools

Diagnose and fix failing ToolUniverse tools through systematic error identification, targeted fixes, and validation.

First Principles for Bug Fixes

Before writing any fix, ask: why does the user reach this failure state?

1. Prevent, don't recover — fix the root cause so the failure can't happen, rather than adding hint text after it does
2. Validate at input, not at output — wrong parameters, unknown disease names, unsupported drugs should be caught and rejected early with clear guidance, not discovered after a silent API call
3. Don't mask silent mutations — if input is auto-normalized (fusion notation, Title Case), either accept both forms natively OR reject with explicit guidance; never silently transform and hide it
4. Distinguish "no data" from "bad query" — zero results because the filter is wrong is different from zero results because the data doesn't exist; the response must distinguish these clearly
5. Fix the abstraction, not the instance — if a parameter name is inconsistent, fix the interface; don't add an alias list that grows forever

Anti-patterns to avoid:

• Adding hint text to zero-result messages instead of validating upfront
• Adding parameter aliases instead of fixing naming consistency
• Post-hoc probing to rescue a failed query instead of pre-validating

Bug Verification (CRITICAL)

Before implementing any bug report, verify it via CLI first:

python3 -m tooluniverse.cli run <ToolName> '<json_args>'

Many agent-reported bugs are false positives caused by MCP interface confusion. Always confirm the bug is reproducible before implementing a fix.

Instructions

When fixing a failing tool:

1. Run targeted test to identify error:

python scripts/test_new_tools.py <tool-pattern> -v

1. Verify API is correct - search online for official API documentation to confirm endpoints, parameters, and patterns are correct

1. Identify error type (see Error Types section)

1. Apply appropriate fix based on error pattern

1. Regenerate tools if you modified JSON configs or tool classes:

python -m tooluniverse.generate_tools

1. Check and update tool tests if they exist in tests/tools/:

ls tests/tools/test_<tool-name>_tool.py

1. Verify fix by re-running both integration and unit tests

1. Provide fix summary with problem, root cause, solution, and test results

Where to Fix

Error Types

1. JSON Parsing Errors

Symptom: Expecting value: line 1 column 1 (char 0)

Cause: Tool expects JSON but receives binary data (images, PDFs, files)

Fix: Check Content-Type header. For binary responses, return a description string instead of parsing JSON. Update return_schema to {"type": "string"}.

2. Schema Validation Errors

Symptom: Schema Mismatch: At root: ... is not of type 'object' or Data: None

Cause: Missing data field wrapper OR wrong schema type

Fix depends on the error:

• If Data: None → Add data wrapper to ALL operation methods (see Multi-Operation Pattern below)
• If type mismatch → Update return_schema in JSON config:
• Data is string: {"type": "string"}
• Data is array: {"type": "array", "items": {...}}
• Data is object: {"type": "object", "properties": {...}}

Key concept: Schema validates the data field content, NOT the full response.

3. Nullable Field Errors

Symptom: Schema Mismatch: At N->fieldName: None is not of type 'integer'

Cause: API returns None/null for optional fields

Fix: Allow nullable types in JSON config using {"type": ["<base_type>", "null"]}. Use for optional fields, not required identifiers.

4. Mutually Exclusive Parameter Errors

Symptom: Parameter validation failed for 'param_name': None is not of type 'integer' when passing a different parameter

Cause: Tool accepts EITHER paramA OR paramB (mutually exclusive), but both are defined with fixed types. When only one is provided, validation fails because the other is None.

Example:

{
  "neuron_id": {"type": "integer"},      // ❌ Fails when neuron_name is used
  "neuron_name": {"type": "string"}      // ❌ Fails when neuron_id is used
}

Fix: Make mutually exclusive parameters nullable:

{
  "neuron_id": {"type": ["integer", "null"]},      // ✅ Allows None
  "neuron_name": {"type": ["string", "null"]}      // ✅ Allows None
}

Common patterns:

• id OR name parameters (get by ID or by name)
• acronym OR name parameters (search by symbol or full name)
• Optional filter parameters that may not be provided

Important: Also make truly optional parameters (like filter_field, filter_value) nullable even if not mutually exclusive.

5. Mixed Type Field Errors

Symptom: Schema Mismatch: At N->field: {object} is not of type 'string', 'null'

Cause: Field returns different structures depending on context

Fix: Use oneOf in JSON config for fields with multiple distinct schemas. Different from nullable ({"type": ["string", "null"]}) which is same base type + null.

6. Invalid Test Examples

Symptom: 404 ERROR - Not found or 400 Bad Request

Cause: Test example uses invalid/outdated IDs

Fix: Discover valid examples using the List → Get or Search → Details patterns below.

7. API Parameter Errors

Symptom: 400 Bad Request or parameter validation errors

Fix: Update parameter schema in JSON config with correct types, required fields, and enums.

8. API Key Configuration Errors

Symptom: Tool not loading when API key is optional, or api_key parameter causing confusion

Cause: Using required_api_keys for keys that should be optional, or exposing API key as tool parameter

Key differences:

• required_api_keys: Tool is skipped if keys are missing
• optional_api_keys: Tool loads and works without keys (with reduced performance)

Fix: Use optional_api_keys in JSON config for APIs that work anonymously but have better rate limits with keys. Read API key from environment only (os.environ.get()), never as a tool parameter.

9. API Endpoint Pattern Errors

Symptom: 404 for valid resources, or unexpected results

Fix: Verify official API docs - check if values belong in URL path vs query parameters.

10. Transient API Failures

Symptom: Tests fail intermittently with timeout/connection/5xx errors

Fix: Use pytest.skip() for transient errors in unit tests - don't fail on external API outages.

Common Fix Patterns

Schema Validation Pattern

Schema validates the data field content, not the full response. Match return_schema type to what's inside data (array, object, or string).

Multi-Operation Tool Pattern

Every internal method must return {"status": "...", "data": {...}}. Don't use alternative field names at top level.

Finding Valid Test Examples

When test examples fail with 400/404, discover valid IDs by:

• List → Get: Call a list endpoint first, extract ID from results
• Search → Details: Search for a known entity, use returned ID