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

The readOnlyHint annotation already covers the safety profile, so the description only needs to add behavioral context. It does add one useful constraint—does not follow calls across projects—but does not disclose other behaviors like traversal direction, cycle handling, or what the returned dependency closure actually contains.

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 short sentences with no filler. The core purpose is front-loaded, and the key limitation follows immediately. Every word earns its place.

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 in schema complexity, but there is no output schema and no parameter descriptions. The description leaves important gaps: what kinds values are accepted, how depth interacts with the closure, what the return value looks like, and which sibling should be used for cross-project scenarios. This is insufficient for fully confident invocation.

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%, so the description must compensate for undocumented parameters. The phrase 'around a selector' gives some context for the selector parameter, but depth and kinds receive no explanation, and 'kinds' is especially ambiguous. The description does not materially reduce parameter misuse risk.

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 identifies the operation as computing a dependency closure anchored around a selector, and it clarifies an important boundary: it does not follow calls across projects. This distinguishes it from generic fetch/search/lookup siblings, though the description lacks an explicit verb making the action fully explicit.

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 when to use the tool: when you need dependency closure for a selector. It also gives an explicit exclusion: not for cross-project dependency traversal. It stops short of naming an alternative for cross-project cases, so it doesn't fully meet the bar for explicit alternatives.

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