query_graph

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses automatic indexing, AST-based parsing (no LLM), filtering logic, and fallback behavior. With no annotations, this fully covers behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise (4 sentences), front-loaded with purpose, and every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, schema coverage, and presence of output schema, the description covers key aspects: filtering, indexing, no-LLM, and referral to sibling for deep analysis.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so description adds no new param details. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Search code graph' as verb+resource, and differentiates from sibling tools by explaining filtering behavior and suggesting summarize_function for deeper analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context on when filtering applies (if preprocess_config was called) and directs to summarize_function for deeper analysis, but does not explicitly state when to use other siblings like get_callers or get_callees.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.