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

With no annotations, the description carries the full behavioral burden and does so thoroughly: deterministic, grounded and signed output ('signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible', 'No LLM; every claim carries its source and retrieval time'), the payment gate with its exact failure behavior ('unpaid call returns the payment requirements (isError)'), and the full output envelope ('settled / transaction / network / payer plus the signed report'). This is substantially more behavioral disclosure than the schema or 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 purpose arrives in the first sentence, and each subsequent clause earns its place: the checks, the input format, the deterministic/signed property, the reference cap, and the payment flow. The detail density is high but justified by the unusual combination of payment, signing, and retraction checks; only the packed middle segment (proof/signing details and payment) could be restructured slightly for scanability.

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 tool with no output schema and no annotations, the description is nearly complete: it covers input constraints, behavior, limits, failure mode, cost, and return value composition. The remaining gaps are minor — the behavioral effect of strict_authors / include_unpaywall is not described, and handling of reference items that fail to resolve is not covered — but they are evident enough to keep this out of perfect.

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 67%, placing this in mid-range territory where description must still compensate for gaps. The description adds the effective 50-reference cap (the schema allows up to 200) and states that input is either structured references or BibTeX. However, the only nested object, 'options' — with strict_authors and include_unpaywall — receives zero semantic meaning in the description, so a meaningful portion of the input surface is left for the agent to guess.

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 verb and resource — 'Verify a bibliography' — then lists a precise checklist of checks (exists, resolves, retracted/corrected/flagged, title/author/year match, fabrication risk). It differentiates itself from siblings by explicit constraints: 'standard tier', 'Up to 50 references' (setting it apart from citation_report_large), the signed-report delivery (vs. citation_report_receipt), and the paid gate (vs. citation_report_preview).

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 provides clear context — paid standard tier, up to 50 references, full verification with signing — which implies when this tool is appropriate. However, it never names the alternatives or states explicit conditions like 'use citation_report_preview to test without paying' or 'use citation_report_large beyond 50 references'. An agent must infer the routing from the tier/limit details rather than read it.

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