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

Annotations already declare readOnly/destructive/idempotent, but the description adds genuinely useful context beyond them: the pricing model ($0.002/call, first 25 free, failed calls free), the 'repeats are not free' billing caveat, and the interpretation caveat that 'ok means no listed flags, not a safety guarantee'. These are real behavioral disclosures not present in structured fields.

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 return contents, then ecosystems, alternative tool, example, pricing and safety caveat. Dense but every sentence earns its place; could be marginally tighter but no filler.

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 carries the full burden and does: it enumerates the returned signals, the supported ecosystems, the version-param behavior, pricing, and a caveat about interpreting 'ok'. Nothing an agent needs 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 100% (baseline 3), and the description still adds value: the worked example (ecosystem=npm, name=lodash, version=4.17.20) plus the behavioral effect of the optional version param ('adds pinned-version metadata and uses deps.dev advisories') and the note that ranges/tags are rejected. Goes beyond the schema's field docs.

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 ('Reports package existence, latest version and release, age, version count, downloads, licenses, deprecation and advisory severity') and explicitly distinguishes itself from the sibling package_audit. An agent can tell exactly what this returns versus the audit tool.

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 when-to-use ('Use before adding a dependency') and names the alternative with its differentiator ('use /package-audit for OSV affected ranges and dated FIRST EPSS CVE estimates'). Routing is unambiguous.

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