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

The readOnlyHint annotation already establishes this as a safe read operation, and the description adds that it checks 'citation and recency metadata coverage' — useful but minimal additional context. No contradiction exists, and it does not describe what the tool returns or how the diagnostic is presented to the agent.

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?

A single, front-loaded sentence with the key verb 'diagnostic' near the beginning. However, the adjective 'Free' is confusing in a tooling context and the dense jargon ('evidence-hygiene') forces a second read, slightly detracting from an otherwise tight structure.

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?

Considering the tool's simplicity (2 params, readOnly annotation), the description covers the diagnostic's input at a high level and names the analysis dimensions (citation, recency). It is adequate as a minimum, but omits any output/return behavior, which is notable given the absence of an output schema, and fails to clarify how this differs from the co-located 'rag_quality_report' sibling.

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 description coverage, the description carries the entire burden. It loosely maps claims→evidence and sources→metadata coverage, which adds mild meaning, but it stops short of clarifying the expected structure of 'sources' objects or the relationship between the two arrays.

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 identifies a diagnostic action applied to RAG claims and sources, mentioning specific aspects covered (citation and recency metadata coverage). It's specific about the resource and scope, though it doesn't explicitly differentiate itself from the similar-sounding sibling 'rag_quality_report'.

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 word 'diagnostic' implies it should be used to evaluate RAG evidence quality, but there is no explicit when-to-use, when-not-to-use, or alternative guidance. Sibling tools like 'repair_structured_output_plan' and 'rag_quality_report' overlap conceptually, and no distinctions are drawn.

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