Check a whole dependency list in one call

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

With no annotations, the description carries the full burden and does most of it: it states the batch ceiling, the return shape (verdict, version to pin, short reason, full notice only for problem packages), and the omit-version fallback to installed version. It does not disclose freshness/latency of the supply-chain lookup or whether checks hit the network, which is the main remaining gap for a tool with zero annotation coverage.

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 what the tool returns, then when to call it, then the version-omission nuance. No filler and nothing repeated from structured fields verbatim.

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?

With no output schema, the description usefully sketches the response (one row per package, full notice only for flagged ones), which is what an agent needs to plan around. Only the ecosystem resolution and any failure/error behavior are unaddressed, a minor gap for a two-parameter read-style 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?

Adds real meaning beyond the schema: the schema only says version can be omitted 'to get the version to use', while the description clarifies that omitting it for packages already in the project means the installed version is checked. It also restates the 50-item cap in prose. The top-level ecosystem default is left entirely to the schema, so not a full 5 at 50% coverage.

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?

Names a specific resource and verb ('supply-chain verdict for up to 50 packages at once') and explicitly scopes the batch nature of the call. It also implicitly contrasts with the single-package sibling by saying 'instead of one check per package', so an agent can route between check-packages and check-package without opening either schema.

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?

Gives a concrete trigger ('Call it once with every dependency you plan to add, before writing the manifest') and a concrete anti-pattern ('one check per package'). The alternative is described rather than named, so the agent must infer that the single-package path is check-package, which stops this short of a 5.

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