audit_packages

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

With no annotations, the description carries the full burden and does so: it discloses that this is read-only (nothing fixed), that pip-audit is fetched on demand by uv so the first call needs network and is slower, and that advisories come from api.osv.dev (a different host from PyPI) so the audit still answers when PyPI is down if the tool is cached. It even calibrates normal output volume (118 advisories across 19 of 286 packages).

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 core purpose in the first sentence, followed by operational context in short, purposeful blocks (calibration, no-fix warning, alternative routing, network/caching notes, then args). Every sentence adds actionable information rather than restating the name.

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?

An output schema exists, so return-value explanation is unnecessary, and the description covers everything else an agent needs: what it does, what it will not do, where to go next, and network/caching behavior. Nothing required to invoke it 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 coverage is 0% for the single `limit` parameter, so the description must compensate; it does explain that limit controls 'how many affected packages to list, worst first,' adding the ordering semantics the schema lacks. It omits the default (40) and any maximum, which is a minor gap given only one parameter.

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 and resource: 'Check the installed packages against the published vulnerability advisories,' and names the concrete mechanism (pip-audit over ComfyUI's interpreter against the OSV database). It also routes the agent away from a sibling by naming plan_packages, so it is distinguishable without opening any 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?

Explicitly states when-not ('Nothing is fixed here, and there is no flag that would') and the alternative to use instead ('Take a finding to plan_packages first'), plus the caveat that `pinned` rows cannot be moved because their version belongs to the CUDA build. The when-to-use and when-not paths are both spelled out.

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