Audit the User Library

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds the behavior of reading every manifest and verifying files, plus the explicit guarantee that recommendations never modify the library, which is useful but mostly aligns with the annotations. No contradiction.

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, front-loaded with the core action and scope, and ends with the non-modification guarantee. No filler or redundant information.

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?

There is an output schema and the core function is described, but the description lacks explanation of the 'includeArchived' parameter and does not differentiate this tool from the similar 'figure_library_reconcile' sibling. It is adequate but leaves gaps for a multi-tool environment.

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?

With 0% schema coverage, the description must compensate for parameter meaning. It indirectly hints at the 'scope' enum values by mentioning invalid, legacy, and duplicate evidence, but it does not name the parameter or explain 'includeArchived'. This is incomplete.

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 tool reads every user-template manifest, verifies stored files, and reports invalid, legacy, and duplicate evidence. It uses specific action verbs and a defined resource, and explicitly notes it never modifies the library, distinguishing it from mutation-type 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?

The description implies usage for auditing and checking the library, and the non-modification note hints at when not to use it. However, it does not explicitly state alternatives (e.g., reconcile) or give clear 'when to use vs. not use' guidance.

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