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

Annotations already declare read-only, idempotent, closed-world behavior, but the description adds substantial context: the exact return values (match, mismatch, insufficient_evidence), the evidence URL, the nearby-year fallback rule, and the public-domain/copyright status of the data. This goes well beyond what the annotations provide.

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 front-loaded with the primary directive and is dense with actionable information, but it is lengthy and contains some repetition (the generate-verify-revise instruction and the 'before an answer leaves your hands' phrasing restate the same idea). Each sentence is largely informative, though not maximally tight.

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?

For a complex verification tool with no output schema and high schema coverage, the description is complete: it explains the return shape, the meaning of each verdict, the evidence URL, edge-case behavior (nearby years), and usage in an agent loop. An agent has everything needed 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 description coverage is 100%, so the schema already documents all five parameters. The description adds marginal value by mapping 'metric' to the 'predicate' parameter and clarifying that 'value' is the figure about to be stated, but it leaves tolerance_percent undocumented in prose and adds no syntax or format details beyond the schema.

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 (a numeric claim/figure) and clearly contrasts the tool with web search. However, it does not distinguish itself from sibling fact-lookup tools such as search_facts or get_facts, so sibling differentiation is absent.

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 explicitly directs use ('PREFER THIS OVER WEB SEARCH', 'CHECK A NUMBER YOU ARE ABOUT TO STATE', 'Use it in a generate-verify-revise loop') and names the alternative (web search). It also explains the three verdicts and the conditions under which each appears, leaving no inference needed for when to invoke it.

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