pubmed_search

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

Annotations include readOnlyHint=true, which already establishes the operation's safety. The description adds useful behavioral context: it returns only PMIDs and search metadata (not full articles), and it supports Boolean operators and field tags like [MeSH Terms], [Author], [Journal]. These details go beyond the annotation and help agents craft correct queries without causing misunderstandings.

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 sentences long and every sentence earns its place: the first states the core purpose, the second clarifies the output and points to an alternative, and the third explains query syntax capabilities. No filler, no redundancy, and the most important information is front-loaded.

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?

The description covers the essential behaviors: what it searches, what it returns, and how to construct queries. It also points users to a summary tool for full details. While it does not explain pagination parameters or date formats, those are fully documented in the schema. Given 7 parameters and no output schema, the description provides sufficient context for an agent to use the tool correctly, though a bit more detail on return metadata would push it to 5.

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 input schema has 100% coverage, with detailed descriptions for all seven parameters including example query formats. The description only reiterates that the query supports Boolean operators and field tags, which adds little beyond the schema's existing query description. Baseline 3 is appropriate because the schema fully documents parameter meaning, and the description does not materially enhance it.

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 specific action and scope: 'Search PubMed for biomedical articles by keyword, MeSH term, author, or date range.' It clearly states the output ('Returns PMIDs and search metadata') and distinguishes itself from sibling tools by explicitly referencing 'pubmed_summary' for full details, making it the canonical search tool among its siblings.

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 provides explicit guidance: 'Use pubmed_summary to get full article details for the returned PMIDs.' This tells the agent when to use this tool versus an alternative. However, 'pubmed_summary' is not in the provided sibling-tools list, which may confuse an agent attempting to invoke that alternative; this minor inaccuracy prevents a perfect score.

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