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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), yet the description still discloses non-obvious behaviour: only names and versions are read, workspace/git/path/url entries are skipped, and matching is done against known advisories by exact version rather than by code analysis. That limitation is the single most important thing an agent needs to avoid over-claiming results.

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?

Front-loaded with the usage trigger, then inputs, then outputs, then limits – a sensible order. It is somewhat repetitive, listing the ecosystem and lockfile enumerations twice and re-explaining return contents despite an output schema existing.

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 trigger, accepted inputs, default behaviour, output shape and explicit non-capabilities. With an output schema present it need not have described fix_first at all, so nothing an agent needs to call this correctly is missing.

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 100%, so the baseline is 3. The description restates the accepted lockfile formats and the 'only names and versions are read' rule that the schema already documents, adding only the default of 3 for fix_first and confirmation that packages takes exact versions.

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 (triage) and resource (dependency vulnerabilities) and immediately narrows scope with example user intents. It is clearly distinguishable from the sibling lookup tools check_cve/check_cves, which handle individual advisories rather than prioritising a whole manifest.

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 explicit trigger conditions plus two verbatim example queries, and adds a negative boundary ('it does not scan code or show that the vulnerable code is reached'). It stops short of naming check_cve/check_cves as the alternative for single-CVE lookups, so routing between siblings is left partly to inference.

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