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

Goes well beyond the readOnly/destructive annotations: discloses detail and subrequest caps, that omissions are explicit rather than silent, that missing evidence is 'unknown, not zero risk', that outputs are automated signals not a safety guarantee, and the full pricing model ($0.01/call via x402 USDC or card key, first 25 free, failed calls free). The 'each call is charged, so repeats are not free' line coherently explains the idempotentHint=false annotation.

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 capability, then caveats, then a usage trigger and example, then pricing — a sensible order. It is dense but most sentences carry real information; the pricing sentence is long and 'See the buying guide for limits' is a soft pointer that costs a little space.

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 only one parameter, no output schema, and open-world behavior, the description compensates well: it names the return fields (advisory IDs, affected/fixed ranges, EPSS), warns that coverage may be incomplete, and sets expectations that the tool is advisory-only. An agent has enough to decide and call correctly.

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% and the single parameter is well documented, so the schema carries the format burden. The description still adds value with a concrete example ('packages=npm:lodash@4.17.20,pypi:requests@2.31.0,npm:@types/node@22.0.0') and the scoped-npm note, reinforcing the encoding an agent must produce.

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 up to 10 public dependencies') and enumerates exactly what it returns: advisory IDs, OSV affected/fixed ranges, and dated FIRST EPSS CVE estimates. Scope limits (max 10, optional exact pins, scoped npm names) clearly separate it from generic sibling tools like package, pypi, or semver.

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?

'Use before installing or upgrading dependencies' gives an explicit trigger context. However, no sibling alternative is named for the case where the agent only needs version/download metadata (e.g., package, npm_downloads, pypi), so the when-not guidance is left implicit.

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