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

Annotations already indicate read-only, open-world, and idempotent behavior. The description adds meaningful detail beyond those annotations by listing possible verdicts and the concrete evidence categories returned, such as per-version deprecation, yanked/retracted releases, repository push dates, maintainer/dependent counts, and advisory IDs. It does not cover failure modes or response structure, but the added context is substantive.

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?

The description is dense but efficient: the opening question frames the verdict, the evidence list is a compact enumeration, and the final sentence gives the invocation context. There is no filler or repetition of schema fields, and the most important information is front-loaded.

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?

Since there is no output schema, the description appropriately carries the return-value burden by naming the verdict categories and the exact evidence an agent should expect. It leaves some details unspecified, such as response structure and error handling, but for a read-only health-check tool the provided information is sufficient for an agent to predict behavior.

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%, with each parameter already documented, including the version parameter's note that omitting it checks the latest. The tool description adds little new parameter-level meaning: it references the exact version, but this is already captured in the schema. A baseline of 3 is appropriate when the schema does the heavy lifting.

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 opens with a concrete question and states exactly what the tool returns: a single verdict among deprecated/archived/stale/active/unknown plus a rich evidence list. This clearly identifies the resource and outcome, though it does not explicitly contrast itself with sibling tools like deps_audit or runtime_eol.

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 explicitly states when to use: 'Use when choosing, pinning or upgrading a dependency' across eight named ecosystems. This is a clear and actionable trigger, but it does not mention when not to use this tool or name alternative sibling tools.

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