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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds meaningful context beyond those: it specifies the data sources (OSV.dev, deps.dev, npm registry), the verdict thresholds (BLOCK/CAUTION criteria), and a feedback fallback (report_feedback with specific parameters). This goes well beyond what annotations alone convey, making behavior fully transparent.

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 long but densely informative. It is front-loaded with purpose and differentiator, then parameters, verdict criteria, sources, and feedback instructions. Every sentence serves a purpose, though it could be trimmed (e.g., repeating 'Read-only' and 'Idempotent' that annotations already state). Slight redundancy prevents a 5.

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?

The description is complete for a tool with 2 parameters, high schema coverage, and an output schema. It covers purpose, usage context, parameter semantics, verdict criteria, data sources, and a feedback path. Since the output schema exists, return format details are unnecessary. No critical information 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% with each parameter already documented, so the baseline is 3. The description adds value by explaining the consequence of providing vs omitting the lockfile (pinned versions vs semver ranges) and reinforces the 500 KB constraint. This exceeds the schema's basic descriptions, so a 4 is warranted.

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 states a specific verb ('Audit'), resource ('frontend package.json'), and outcome ('returns a single SHIP/CAUTION/BLOCK verdict with licence risks and abandonment signals'). It explicitly distinguishes from sibling security_fetch_package_vulnerabilities by scope (full manifest vs single package), so an agent can immediately identify when to use this 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?

The description explicitly contrasts this tool with security_fetch_package_vulnerabilities, stating this one takes the full package.json. It also explains the optional lockfile behavior (pinned vs semver ranges), giving clear context for when to include it. No explicit 'when not to use' beyond the differentiator, but that is sufficient given the specific alternative named.

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