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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows this is a safe read operation. The description adds the behavioral scope ('Every function/method the given function calls') and frames callees as dependencies. However, it does not disclose whether the result includes only direct calls or transitive dependencies, nor any details about ordering or result structure. This is acceptable given the annotations but not fully transparent.

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 concise sentences: the first defines the tool's function and resource, the second provides a reason to use it. No fluff, no repetition of schema or annotation data. The key information is front-loaded in the first sentence.

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 is simple (1 parameter) and has an output schema, so return values are already documented elsewhere. The description covers purpose and usage. The only notable omission is whether callees are direct calls only or transitive dependencies, which could influence agent expectations. But overall, the description is sufficiently complete for a read-only lookup tool with annotations and an output schema.

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% for the single parameter function_name, with a clear example ('sync_repository'). The description does not add parameter-specific information beyond the schema, which is appropriate given the high coverage. Baseline 3 applies because the schema carries the meaning.

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 uses a specific verb ('get') and resource ('callees') and immediately clarifies what it returns: every function/method the given function calls. It distinguishes from sibling tool get_callers by explicitly noting the direction ('calls' vs 'called by') and adds conceptual meaning ('what it depends on to do its job'). The usage hint about not assuming behavior from the name further clarifies the purpose.

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 gives clear context: 'Use this to understand a function's behavior by seeing what it delegates to, before assuming what it does from its name alone.' This tells the agent when to invoke this tool (when behavior is unclear from the name). It does not explicitly name alternatives or state when not to use it, but the guidance is direct and actionable.

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