fetch_abstracts

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

With no annotations, the description carries the full burden and does so unusually well: it discloses auto-dedup, PMID zero-padding/normalization, batching, the return triple (requested count, actual record count, missing IDs), the caveat that a record may exist without an abstract (editorials), and that network failures raise rather than masquerade as empty results.

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?

It is front-loaded with the verb and resource, then layers behavior, workflow advice, and caveats in terse semicolon-delimited clauses. Dense but nearly waste-free; the final caution about verifying numeric citations against the original text is marginally beyond tool scope.

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 one-parameter fetch tool, everything needed to call it correctly is present: input encoding, normalization behavior, return semantics, missing-ID reporting, and failure mode. The output schema exists, yet the extra return-shape summary still adds useful caveat context rather than redundancy.

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?

The single parameter has 0% schema description coverage, and the description compensates directly by specifying the accepted encoding — comma- or space-separated PMIDs — plus implicit normalization of zero-padding and deduplication of inputs.

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 first clause states a specific verb (取/fetch) and resource (NCBI 原排版摘要, by PMID), and it names the format and fidelity guarantee (original formatting, structured sections preserved). An agent can distinguish this from search/count siblings without opening the schema.

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 recommends a concrete workflow — screen the record list first with a search, then fetch only the abstracts needed to save output — which implicitly routes the agent to the search sibling before this one. It gives no explicit exclusion case (e.g., when not to fetch), so it falls just short of a 5.

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