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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the description adds value by detailing that it reads the paper's abstract and full text where available, and that the 'examined field' indicates which source was used. The inclusion of the validation statistic (139/160 agreement) further sets expectations about reliability, which goes beyond the structured metadata.

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 logically organized: it starts with the core function and verdict types, then usage guidance, then source details, and ends with a performance note and link. While it contains some extra detail (the evaluation statistic), it remains concise and front-loaded. Every sentence adds information, though the length could be trimmed slightly without losing substance.

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?

The description covers the essential aspects: what the tool does, when to use it, and what sources it consults. Since an output schema exists (as indicated by the context signal), it correctly avoids explaining return values. The one minor gap is that it doesn't explicitly state what happens if the paper isn't found or if the sentence isn't a citation, but overall it is sufficiently complete for reliable invocation.

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 100% for both required parameters (sentence and cited), and each has a descriptive explanation (e.g., cited accepts multiple forms). The tool description adds little beyond this—it implies the sentence is a citation context, but that's already in the schema. Thus, the baseline of 3 is appropriate because the description does not meaningfully enhance parameter understanding.

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 states a specific verb ('verify') and resource (citation support) and enumerates the exact output categories (supports, partly supports, contradicts, not addressed). It also includes a concrete usage context ('before citing a paper'), which helps distinguish it from sibling tools like check_claim or analyze_paper_claims, even without naming them.

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 gives explicit when-to-use scenarios: 'before citing a paper for a specific claim, or to check a citation in a draft or an answer.' It does not mention alternatives or exclusions, but the stated use cases are clear and actionable, making it easy for an agent to decide when to invoke this tool.

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