audit_dependencies

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

With no annotations, the description carries full burden. It discloses that the tool returns a verified finding, the lead, split, and verdict basis, and states it is deterministic. It does not cover potential side effects or auth requirements, but the behavior is clearly outlined.

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 two sentences, densely packed with information, and front-loaded with the core action ('Audit a single manifest/lockfile'). Every sentence contributes without redundancy.

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 the simple two-parameter input and no output schema, the description adequately covers input format, supported file types, and output components. It lacks error handling or edge cases, but is reasonably complete for the tool's complexity.

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?

Despite 0% schema description coverage, the description explains the two parameters: 'raw lockfile text' corresponds to lockfile_content and 'its filename' to filename, with examples. This adds meaning beyond the schema, though parameter-level details are minimal.

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 it audits a single manifest/lockfile and returns a verified finding. It distinguishes from siblings (audit_project, audit_repo) by focusing on a single file, making the purpose unambiguous.

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 instructs users to pass raw lockfile text and filename, and lists supported file types. It implies this tool is for individual files but does not explicitly contrast with sibling tools for projects or repos, leaving some room for interpretation.

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