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

With no annotations present, the description carries the full burden and does so: it discloses the auth → moderation → credit-charge → verification → refund pipeline, states that credits are charged per call and that inconclusive verdicts are not refunded, gives a concrete latency range, and enumerates the exact error conditions including the disabled-endpoint message.

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?

Front-loaded with the core claim-in/verdict-out framing, then layered detail in short paragraphs that each add distinct information (verdict taxonomy, pipeline, parameters, errors). The 'Returns VerifyResponse (verdict / confidence / reason_code / evidences[] / timing)' line is largely redundant given an output schema exists, a minor waste in 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?

For a 5-parameter tool with an output schema, the description covers what the schema cannot: verdict semantics, cost/refund behavior, latency, error surface, and auth precedence. An agent has everything needed to decide, invoke, and interpret a call 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 0%, and the description fully compensates: mode's three values and the 'auto' default rule (DOI/arXiv signal), evidence_urls' 5-item cap, max_evidence's 1-10 range and default of 5, and api_key's `sp-` prefix plus env-var fallback and precedence order. Every parameter is given meaning the schema does not.

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?

Opens with a specific verb+resource+scope: 'Verify a factual claim against retrieved evidence: claim in, verdict out', and explicitly frames the output as a four-label judgment rather than generated text. It never names the sibling searchpipe_search, so the agent must infer the division of labor (verify vs. retrieve) from context alone.

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?

Usage is implied rather than stated: the verdict-label taxonomy and the 'inconclusive' explanation tell the agent what the tool will judge, and the 5-15 second latency note sets expectations. However, there is no explicit when-to-use versus searchpipe_search, no exclusions, and no guidance on when a claim should be verified instead of merely searched.

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