Audit dependencies/manifests with fix recommendations (paid)

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

Annotations cover only the safety profile (readOnly, idempotent, openWorld, non-destructive); the description goes well beyond by disclosing the billing model ($0.0009/package + $0.0028/vulnerability + per-run fee, with a worked lodash+django example), the required APIFY_TOKEN and account-charging behavior, the paged row types, and the full enumerated error taxonomy. That is exactly the additional context an agent needs before committing to a paid call.

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 label-prefixed structure (WHAT / WHEN / WHEN NOT / COST / RETURNS / EXAMPLE) front-loads the identifying information and makes the routing and cost facts scannable. Despite its length, every section is functional — there is no filler or restatement of the tool 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?

For a 7-parameter, paid, open-world tool with 0 required parameters, the description covers inputs, cost, auth prerequisites, output row types, paging, and failure modes. Because an output schema exists it is not obligated to describe returns, yet the summary of row types still aids invocation.

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, but the description adds real decision value: it tells the agent to set minSeverity="HIGH" specifically to cut vulnerability rows and therefore cost, and the EXAMPLE shows manifestText combined with minSeverity in practice. It does not, however, clarify manifestText-vs-packages precedence or the dev-dependency default beyond what the schema already states.

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 WHAT block names a specific verb (runs an audit), the exact resource (OSV database against a pasted manifest or package list), and the concrete output shape (per-package severity/CVSS, fixed versions, one row per vuln). It explicitly differentiates itself from the two sibling tools osv_query_packages and osv_get_vulnerability, so an agent can route 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?

It gives explicit WHEN (full project audits from a pasted manifest, CI-style reports, severity-filtered output) and WHEN NOT (quick checks of a few exact versions via osv_query_packages, or a single advisory via osv_get_vulnerability), naming both alternatives by name. The condition that selects each path is fully spelled out, leaving nothing to inference.

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