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

Annotations only cover readOnly/openWorld/idempotent; the description goes well beyond them, disclosing the data sources (Crossref, arXiv), the exact verdict semantics (mismatch never reported as verified, near title match never verified, absent title -> not_found, one-year tolerance), and a signed offline-checkable receipt with the issuer key URL. That is unusually rich behavioural context for a read-only tool.

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?

Purpose and required input are front-loaded in the first two sentences, and the longer clauses on comparison semantics and the signed receipt each carry useful information rather than filler. It is dense and somewhat run-on, but nothing is clearly expendable.

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?

With no output schema, the description does the work of sketching the return payload (existence, title, authors, year, container, retraction/citation status) and the possible verdicts, which is what an agent needs to interpret results. Minor gaps remain around error/limited-coverage cases, but the picture is essentially complete for a 5-parameter read tool.

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 baseline is 3, but the description adds genuine meaning about how the parameters interact: the claimed_* fields are all optional and each is compared one-by-one against the record, with disagreements surfaced as mismatch rather than a pass. It still doesn't restate format constraints like maxLength or the surname-comparison rule beyond what the schema says.

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 and resource — checking whether a citation's metadata exists, is correct, and has been retracted — and names concrete inputs (DOI, arXiv ID, title). It does not explicitly differentiate itself from near-neighbours like check_document, check_entity or verify_bulk, but the citation/DOI scope is unambiguous enough to route correctly.

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 implies usage by describing the two modes of the tool (bare lookup vs. comparison against claimed fields) and the meaning of verdicts, but never says when to choose this over verify_bulk, check_document or verify_package, nor any when-not condition. The agent must infer the boundary from the resource type alone.

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