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

Annotations include readOnlyHint=true and openWorldHint=true. The description adds behavioral context: it mentions PubMed's limit of 9999 records (offset cap at 9998) and the note about summarizing with a cap of 50, directing to pubmed_fetch_articles for remaining PMIDs. It also clarifies date range behavior (only applied when both minDate and maxDate are non-empty) which is in the schema but the description sets expectations. These are useful beyond annotations. Not a contradiction.

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 a single paragraph that is relatively concise given the tool's complexity (14 parameters). It front-loads the main purpose and return type, then lists key capabilities. It doesn't repeat schema details, so it's efficient. Could be slightly more structured (e.g., bullet points) but overall good.

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 tool is complex with 14 parameters, but the schema covers all parameter details and the output schema exists. The description adds important context about pagination limits, summarization limits, and the hint to use another tool. It does not explain the output schema, but that is not required when output schema is provided. Overall, 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 100%, so parameters are well-documented in the schema. The description adds a few semantic details beyond the schema: it explicitly mentions that offset is 0-based and that PubMed serves at most 9999 records, and that summaryCount above 50 requires passing PMIDs to a sibling. These are minor clarifications, but since the schema already covers parameters, a high score is appropriate. The description doesn't fully compensate for anything missing, but adds a little value.

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 states a specific verb ('Search') and resource ('PubMed') with explicit scope: 'full query syntax, filters, and date ranges'. It also indicates return type ('PMIDs and optional brief summaries') and supports pagination. This clearly distinguishes it from siblings like pubmed_fetch_articles or pubmed_convert_ids.

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 clearly states what the tool does, including filters and pagination, but does not explicitly mention when not to use it or direct to alternatives. It implies usage for searching PubMed, and mentions 'pagination via offset' which is a usage pattern. However, it doesn't name specific sibling tools or conditions for when to choose them instead (e.g., when to use pubmed_fetch_articles for full text). Thus, it's clear context but lacks explicit exclusions.

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