PubMed 文献検索

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

With no annotations, the description carries the full burden of behavioral disclosure. It states that results include source URL and acquisition datetime, and implies that full abstracts are NOT returned by directing to fetch_pubmed_abstract. This is useful behavioral context. It doesn't mention rate limits or pagination, but these are less critical for a search tool and may be covered by the output schema.

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 three short sentences, each adding value. The purpose is front-loaded, the filtering options are summarized, and the follow-up action is clearly stated. There is no redundant or filler language.

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 the tool's complexity (9 parameters, 1 required) and the presence of an output schema, the description covers the essential information: purpose, key filtering capabilities, and a usage hint for abstracts. It doesn't explain every parameter or edge case, but the schema and output schema likely cover return details. Overall, it is sufficiently complete for an agent to call it correctly.

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 0%, so the description must compensate. It lists the conceptual filter dimensions (keyword, author, journal, year, study design), which maps to most parameters. However, it doesn't mention sort, limit, or free_full_text, though those are somewhat self-evident. The high-level mapping is helpful but not exhaustive, leaving some parameter details to the schema names and defaults.

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 clearly states the tool performs a search over PubMed and returns a list of bibliographic information. It uses a specific verb ('search'), a specific resource ('PubMed'), and an explicit outcome, which distinguishes it from sibling tools like search_clinical_trials and search_drug. It also names fetch_pubmed_abstract as a follow-up, reinforcing its role as the search step.

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 explicitly instructs when to call fetch_pubmed_abstract next, providing a clear workflow. While it doesn't explicitly say when NOT to use other search tools, the focus on PubMed and the mention of abstract retrieval as a separate step is enough to guide usage. It could be improved by explicitly naming alternative search tools, but the main alternative is covered.

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