PubMed 抄録取得

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

With no annotations, the description carries the disclosure burden and does well: it states the abstract is returned verbatim with no summarization/translation/interpretation, and that structured abstracts are split by section. It does not cover failure modes or edge cases such as missing abstracts, but the core behavior is transparent.

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?

Three short sentences, each adding distinct information: retrieval scope, verbatim behavior, and structured-abstract handling. No filler or redundancy.

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 simple fetch-by-ID tool with an output schema available, the description covers the main behavioral facts and return characteristics. It lacks guidance on invalid/missing PMIDs or array size behavior, but those are minor against an otherwise complete picture.

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 only minimally compensates by saying 'specify PMID'. It does not clarify that pmids accepts an array, what counts as a valid PMID, or any limits; however, the single parameter's name and type are semantically obvious.

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 uses a specific verb ('取得します') and resource ('抄録の全文と書誌情報') keyed to PMIDs, making the operation concrete. It is clearly distinct from sibling search_pubmed, which searches rather than fetches by ID.

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 implies the tool is for when PMIDs are already known, but it does not explicitly state that search_pubmed should be used to discover PMIDs or exclude alternative retrieval paths. Usage context is only inferred, not stated.

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