codegraph_callees

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds a behavioral nuance about using the file parameter to select a definition, which is useful. However, it does not disclose return format, pagination, or handling of multiple definitions. With annotations present, the added value is modest but not negligible.

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 a single, front-loaded sentence that states the core action and the optional file disambiguation. There is zero waste; every word earns its place. It is appropriately concise for a tool of this complexity.

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?

The tool has 4 parameters (one required) and no output schema. The description provides only a high-level purpose and a hint about file selection, but does not explain the required symbol parameter, the limit default, or any edge cases. Given the required parameter is undocumented and the description adds no details, an agent would be under-equipped to call this tool correctly without additional research.

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 50%: file and projectPath have descriptions, while symbol (required) and limit have none. The description does not compensate for the undocumented parameters—it never explains what 'symbol' should be (e.g., a function name, a qualified name) or what 'limit' controls. This leaves the agent guessing about the required parameter, so the description adds no value beyond the schema for these fields.

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?

The description states a specific verb ('Find') and a clear resource ('functions and methods called by a symbol'). It also distinguishes from sibling codegraph_callers by explicitly noting 'called by' rather than 'callers'. The purpose is unambiguous and well-scoped.

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 implies usage (you use this to find callees) but provides no explicit when-to-use guidance or alternatives. It does hint at the file parameter's role ('optionally selecting its definition by file'), which gives some context, but there is no mention of sibling tools or when to prefer this over codegraph_callers.

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