dependency_graph

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

Annotations already declare the safe read-only, idempotent, non-destructive profile. The description adds real behavioral context beyond them: results are 'direct' (one hop, non-transitive) and bounded to the local index, meaning stale or incomplete coverage is possible. It still says nothing about truncation behavior with max_results, so a 3 is appropriate.

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?

A single front-loaded sentence with a semicolon-separated scope caveat; no filler or restatement of the name. Dense and efficient, though it is brief enough that some useful detail is omitted rather than wasted.

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?

For a four-parameter tool with 0% schema description coverage and no output schema, the description leaves the agent guessing on parameter values, repo_path semantics, and result truncation. Annotations cover safety, but they cannot fill the parameter gap that this terse description also fails to fill.

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 0% for all four parameters. The description conveys that symbol and direction (callers vs callees) exist, but it never states the direction values ('out'/'in'), what repo_path must point at, or that max_results truncates results, so it does not compensate for the schema gap.

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?

States a specific verb (query) and resource (indexed symbol-reference edges) with scope (direct callers or callees), which lets an agent distinguish it from generic search tools like search_code or find_symbol. It does not name a sibling explicitly, so it stops short of a 5.

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 stated output (direct callers/callees) implies when the tool is relevant, and 'evidence is limited to the local index' is a useful usage caveat about incomplete results. However, there is no when-not guidance and no routing to alternatives like find_symbol or search_code, so guidance is only implied.

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