dependency_auditor__audit_npm

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that versions are read from lockfiles with a documented fallback to package.json ranges (implying ranges yield less accurate results) and that OSV is an external lookup, but it never states read-only nature, network/privacy implications of sending dependency data, or rate limits. Adequate but incomplete for a no-annotation tool.

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?

Two dense sentences, front-loaded with the action and data source; the lockfile enumeration earns its length by telling the agent exactly which inputs are honored without needing to consult external docs.

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 annotations and no output schema, the description should cover more of the call contract. It fully explains input resolution but says nothing about the shape of findings, severity ordering (only hinted via the exploitData schema field), or that the tool performs an external lookup. Enough to invoke, not enough to be confident about results.

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 schema already documents directory, exploitData, and includeDevDeps thoroughly, including defaults. The description adds no parameter-level meaning beyond the lockfile resolution behavior, so the baseline 3 applies.

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 (Audit) and resource (npm dependencies) plus the mechanism (OSV database), and enumerates the exact lockfile formats resolved (package-lock.json, pnpm-lock.yaml, yarn.lock v1/berry, bun.lock). This is clearly distinguishable from the sibling ecosystem tools audit_pip and from slopsquat_scanner__scan_npm, which targets hallucinated packages rather than CVEs.

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 context of use (an npm project with a lockfile) is implied, but there is no explicit when-to-use vs the siblings audit_package / audit_directory, nor any exclusion or prerequisite guidance. An agent must infer which of the four dependency_auditor tools to pick from scope alone.

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