scan_project

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

No annotations are supplied, so the description carries the full burden and does so well: it declares read-only, caps recursion at 3 levels, skips node_modules/virtualenvs, states result ordering ('worst first') and that advisories are merged (GHSA/PYSEC/CVE) with transitive dependency paths. It omits what happens on an unsupported or unreadable lockfile, whether network access to OSV.dev is required, and any error behavior.

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 purpose, then input forms, then supported formats, then output shape. The format enumeration is long but earns its place by preventing calls on unsupported files; the paragraph form is slightly dense compared to a bulleted list.

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 2-parameter scan tool with an output schema, the description covers inputs, supported ecosystem coverage, ordering, and dedup/merge behavior thoroughly. The main residual gaps are error handling for unsupported files and any note that the scan requires reaching OSV.dev.

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 0%, and the description compensates strongly for both parameters: `path` is defined as either a directory (with depth/skip rules and a full list of accepted lockfile formats/pin styles) or a single lockfile, and `limit` is explained as capping vulnerable packages listed per lockfile. It still lacks details an agent must guess, such as whether `path` is relative to the working directory or absolute and how non-matching pins in requirements.txt are treated.

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 ('Scan a project's lockfiles for known vulnerabilities') plus the data source (OSV.dev), making it clearly distinct from check_package (single package) and list_outdated (outdated, not vulnerable) among the siblings.

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?

Clearly signals the input scope: a project directory versus a single lockfile, including the recursion depth and skipped directories. It gives the agent a concrete picture of when this tool applies, but never names the alternatives (check_package, list_outdated) or states exclusions explicitly, leaving sibling routing to inference.

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