trace_callees

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

No annotations exist, so the description carries full burden. It discloses the default filtering behavior and that the output shape matches 'find_callers'. However, it does not mention whether the tool is read-only, has destructive side effects, or any rate limits or auth requirements.

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?

Two sentences that are front-loaded with the core purpose and immediately useful behavioral detail. Every word earns its place; no 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?

With 9 parameters and no output schema, the description is incomplete. It only addresses the 'include' parameter and does not explain output format, usage of other parameters, or how to interpret results. The tool's complexity demands more comprehensive documentation.

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 only 22%, but the description adds value by clarifying the 'include' parameter (values like common_methods and unresolved and their default behavior). Other parameters (e.g., id, ref, edge_kinds, resolution) remain undocumented, partially compensating but insufficient to fully cover the 9 parameters.

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 'Find what a symbol calls (forward call graph)', providing a specific verb and resource. It distinguishes itself from the sibling tool 'find_callers' (reverse direction) by referencing the same evidence shape.

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?

Description explains that unresolved and common-method noise is filtered by default and how to include it via the 'include' parameter. It implies usage for discovering outgoing calls, but does not explicitly state when to use this tool over siblings like 'find_callers' or other graph tools.

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