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

Annotations already declare readOnly, idempotent, and non-destructive, so the description adds valuably by disclosing edge-case behavior: possible return states like 'skipped' and 'no_passage,' and the warning that 'The judge is not a source.' This goes well beyond the annotation hints.

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 concise and front-loaded: it states the core action, then invocation pattern, then return behavior. The typo 'noul' (apparently 'null') is a minor blemish that prevents a perfect score, but every sentence earns its place.

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?

Even without an output schema, the description enumerates the key return conditions, input alternatives, and a critical caveat about the judge not being a source. For a 4-parameter tool with strong annotations, this is sufficient for an agent to call it correctly.

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 the baseline is 3. The description adds meaningful grouping and provenance: id comes 'from a search cite,' and source is used 'with doc,' clarifying the two valid invocation forms beyond the schema's individual property descriptions.

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 opens with a specific action and resource: 'Score whether a stored index passage supports a claim.' It also distinguishes itself from sibling search/retrieval tools by emphasizing it uses a stored passage and is 'not a live web fetch.'

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?

It gives clear invocation context: 'Pass id from a search cite, or source plus doc,' which tells an agent when and how to call it. It also warns this is 'not a live web fetch,' but it does not explicitly name sibling tools as alternatives, so it stops short of full when/when-not routing.

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