audit_dependencies

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

With no annotations, the description carries the full burden. It explains the output format (risk table sorted by commitment score) and details the risk flags (CRITICAL, HIGH, WARN) with specific criteria. It does not mention read-only behavior or authentication needs, but the details provided are sufficient.

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 well-structured, starting with the main purpose, then risk flags in bullet points, then use cases and examples. All sentences add value, though it could be slightly more concise.

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?

Given no output schema, the description adequately explains the return format and risk criteria. It covers the tool's scope (batch, up to 20 packages) and provides examples. Missing explicit details on exact output fields but still reasonably complete.

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%, so baseline is 3. The description does not add significant meaning beyond the schema: it restates that packages are a list and ecosystem defaults to npm. The schema already includes examples and limits.

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 clearly states the verb 'batch-score' and the resource 'npm or PyPI packages for supply chain risk'. It distinguishes from sibling tools (lookup_npm_package, lookup_pypi_package) which are for single-package lookups.

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 provides clear context for when to use this tool: auditing a full package.json or requirements.txt, and gives examples like scoring all deps or comparing two packages. However, it does not explicitly exclude using sibling tools for single-package details.

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