check_dependency

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

No annotations, so description carries the burden well: discloses data sources (PyPI, OSV.dev), the anti-hallucination purpose, and the return recommendation values (add | use_existing | avoid). Doesn't cover error behavior or rate/network limits, keeping it below 5.

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?

Three tight sentences, front-loaded with the trigger condition, then what it checks, then the return values. Every sentence 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?

Covers purpose, data sources, and output recommendation shape, but with no output schema and 0% schema coverage on 4 params, it leaves repo/version semantics and the response structure under-explained. Adequate but with clear gaps.

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 0% and 4 parameters exist, but the description only meaningfully implies `purpose` (when it says 'something the project already has covers purpose') and `name` (the package). `repo` and `version` are not explained at all, so significant gaps remain.

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 (check) and resource (dependency) plus the exact checks performed: PyPI existence, vulnerabilities via OSV.dev, maintenance, and existing coverage. Clearly distinguishable from siblings like check_reuse and verify_lean.

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?

Explicitly says 'Call BEFORE adding a package', giving a clear timing/usage anchor. Doesn't name a specific alternative or exclusion scenario, but the trigger condition is clear enough.

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