find_callers

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

No annotations are provided, so the description carries full burden. It discloses return values (call sites with confidence, false-positive risk, memories) and a special edge case (dispatches edges). It does not mention side effects or dependencies, but as a query tool, this is adequate. No contradictions with annotations (none present).

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?

The description is two sentences long, front-loads the core purpose, and adds critical details without redundancy. Every sentence adds value, making it efficient and structured.

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?

No output schema is present, so the description must explain return values, which it does adequately (call sites, confidence, risk summary, memories). It also covers a special case (disambiguation). However, with 9 parameters and no parameter descriptions in schema, the description could be more comprehensive for complex scenarios.

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 description coverage is low (22%), so the description must compensate. It adds context about 'dispatches edges' relating to the `edge_kinds` parameter, but does not explain the other 7 parameters beyond implicit references. For a tool with 9 optional parameters, more explicit guidance would be helpful.

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 the tool's purpose: 'Find what calls a symbol (reverse call graph)'. It uses a specific verb and resource, distinguishes from grepping for call sites, and mentions resolving with symbol_lookup for ambiguous names. Siblings include trace_callees (likely forward direction), so it's well-differentiated.

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?

The description advises to 'Resolve the symbol with symbol_lookup first when a name is ambiguous' and implies using this tool instead of grepping. However, it does not explicitly state when not to use it or compare it to siblings like trace_callees. The context is clear but lacks explicit exclusions.

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