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

Annotations already mark the operation read-only, idempotent, non-destructive, and open-world, so the description does not contradict them. It adds useful scope-level transparency by naming the specific metadata categories included and the exclusions (no abstracts, no full text). It does not cover failure behavior for unknown DOIs, but the safety profile is already well covered by annotations.

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 a single dense sentence that front-loads the core action and then structures the output scope with a compact list of metadata categories. Every phrase earns its place, and there is no filler, restatement of schema fields, or repetition of annotation values.

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?

Given only one required parameter, a rich annotation set, and an available output schema, the description is largely complete for selecting and invoking the tool: a known DOI goes in and normalized Crossref metadata comes out, with explicit exclusions. It only stops short of perfect by not addressing the sibling work-search alternative or acceptable DOI input formats, but those are not critical to a correct call.

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?

With schema description coverage at 0%, the description needed to compensate for the lone doi parameter, but it only restates the concept of 'one DOI' and gives no format guidance such as bare DOI vs doi.org URL or case sensitivity. The parameter name and schema constraints are minimal, and the description adds essentially no meaning beyond the property name itself.

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 concrete verb and resource: 'Resolve one DOI'. It enumerates exactly what kind of metadata will be returned (bibliographic, author, container, citation-count, license, identifier, correction/retraction links) and explicitly excludes abstracts and full text, making it clearly distinguishable from sibling tools like research.crossref-work-search even without opening their schemas.

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 phrase 'Resolve one DOI' clearly implies use when the agent already has a single DOI in hand. However, it does not explicitly state when not to use this tool or mention the sibling research.crossref-work-search as the alternative for query-based search, so the routing guidance is mostly left to inference.

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