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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context by disclosing that the response includes the safety_notes field and instructing the agent to cite it alongside paper details. This goes beyond the annotations and informs response handling, though it doesn't detail error behavior.

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 two sentences, front-loaded with the primary purpose and immediately followed by a critical usage note. Every word contributes value and there is no redundancy or filler.

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?

For a simple fetch tool with good annotations, the description covers the core purpose and an important non-obvious response detail. It lacks explicit usage guidance versus siblings and does not explain the lang parameter, but given the simplicity and available schema, it is adequate and mostly complete.

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 schema describes pmid as 'PubMed identifier' and lang as an enum without further text. The description repeats that it fetches by PMID but does not clarify the optional lang parameter's meaning or the pattern constraint. With 50% schema coverage, the description should compensate but does not, leaving lang semantically underspecified.

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 'Fetch a single paper by PMID', using a specific verb and resource that distinguishes it from sibling tools like get_safety_notes or search_h2_papers. It conveys the exact scope (single paper by PMID) and the unique response field (safety_notes).

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 implies usage for fetching a specific paper by PMID, but it does not explicitly mention when to use it over alternatives (e.g., search_h2_papers for broad searches) or provide exclusions. There is no guidance on when not to use this tool, so the usage context is only implied.

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