pubmed-mcp-server

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

Annotations declare readOnly and openWorld hints. The description adds valuable behavioral context beyond these annotations: it specifies the return format (PMIDs vs summaries), explains pagination behavior for large result sets, and notes support for full NCBI syntax. No contradictions with 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?

Three well-structured sentences with zero waste. First sentence establishes core function and returns (front-loaded). Second sentence details filter categories. Third sentence addresses pagination. Every word earns its place.

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 complexity (14 parameters, nested objects) and presence of output schema, the description provides excellent contextual coverage. It addresses search capabilities, return types, filter categories, and pagination—sufficient for an agent to understand the tool's role in the PubMed tool ecosystem.

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 100% schema coverage, the baseline is 3. The description adds value by conceptually grouping parameters (field-specific filters: author/journal/MeSH vs common filters: language/species/free text) and highlighting the pagination mechanism (offset). It also connects 'optional brief summaries' to the summaryCount parameter, adding semantic context.

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 verb (Search), resource (PubMed), and core capabilities (full query syntax, filters, date ranges). It explicitly distinguishes this as a discovery tool that returns PMIDs, differentiating it from sibling fetch/convert tools without needing to name them explicitly.

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 clear context by specifying the return format (PMIDs and optional brief summaries), which implicitly guides when to use this tool (discovery) versus pubmed_fetch_articles (retrieval). It mentions pagination for large result sets, a key usage pattern. However, it lacks explicit 'when not to use' guidance or direct sibling comparisons.

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