get_callees

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

No annotations exist, so description carries full burden. It correctly describes return of outgoing nodes up to a depth, but omits behavioral details such as response format, pagination, rate limits, or side effects. Since output schema is present, return values need not be detailed, but missing context on potential limits or errors.

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, no wasted words. Purpose and context are front-loaded. Every sentence is essential.

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?

Tool is simple (3 params, output schema). Description covers purpose and typical use. Could benefit from mentioning when to prefer get_callers or cross_language, but overall sufficient for a focused query tool.

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 67% (limit and max_depth described, node_id not). Description does not add meaning beyond schema; it repeats 'outgoing' and 'max_depth' but no extra detail on values or formats. At 67% coverage, description adds marginal value.

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 specifies verb 'Return', resource 'nodes that node_id CALLS' (outgoing), and scope 'up to max_depth hops'. It clearly distinguishes from sibling tools like get_callers (incoming) by explicitly stating outgoing direction and dependency analysis use.

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?

Explicit use case provided: 'Use to understand what a function depends on internally.' While it does not list when not to use or alternatives, the directional clue (outgoing) and sibling names (get_callers, get_cross_language_calls) allow agents to infer context.

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