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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the description doesn't need to repeat those. The description adds meaningful behavioral context by explaining that results are Pubmed's precomputed neighbors ranked by relevance and reveals the input requirement of a single PMID plus the output shape of full citation metadata. It does not contradict any 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?

The description is compact and front-loaded with the core purpose, followed by mechanism, output, and use cases. The sibling differentiation is included at the end without bloating the text. Every sentence 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?

The description is complete for an agent to select and invoke the tool correctly: it explains what the tool does, how it ranks results, what the input is, what the output contains, when to use it, and which sibling to use instead. The absence of an output schema is compensated by the description explicitly naming the return elements (title, authors, journal, date, DOI).

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 coverage is 100%, so the schema already documents both parameters (pmid and limit) including the allowed range and default value. The description adds context that the PMID is a seed article and that results contain full citation metadata, but this is light supplemental context on top of well-covered schema. A baseline 3 is appropriate.

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's function with a specific verb and resource: 'Find papers SIMILAR to a given article' using NIH PubMed's computed 'related articles'. It provides concrete details about the mechanism (shared terms/MeSH/citations) and output (top related papers with full citation metadata). It also differentiates itself from the sibling pubmed_get_citations, which finds citing papers.

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 states when to use this tool with concrete use cases: 'more papers like this', building a reading list from a seed paper, or broadening a literature search beyond keyword matches. It explicitly excludes the alternative tool pubmed_get_citations, clarifying the boundary between the two sibling tools.

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