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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint false), so the description's additional behavioral details are valuable context. It discloses pagination behavior ('Paginate through all citing articles with page_size and page parameters') and the nature of the response (total count plus bibliographic details). No contradictions with annotations. It doesn't mention any rate limits or auth requirements, but those are not expected for a read-only API with open world hint.

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 and front-loads the core function in the first sentence. The subsequent sentences add useful details: return fields and pagination, then use cases. It avoids repeating schema content unnecessarily)Skip the final use-case sentence could be considered slightly verbose, but it earns its place by helping an agent understand the intent. Overall well-structured and appropriately sized.

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 a read-only citation lookup tool. It specifies the required input, the output shape, and pagination. An output schema is present, so the description doesn't need to elaborate further on return values. The use cases and parameter guidance ensure an agent can confidently invoke the tool without additional context. No significant gaps identified.

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 the schema already documents every parameter. The description adds minimal parameter-specific meaning: it emphasizes the id should be a PMID or other source-specific ID, which is redundant with the schema text. It does not add new semantic detail about src, page, or page_size beyond what schema provides. Given full schema coverage, a baseline of 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 specific verb 'Retrieve a list of articles that cite a given biomedical publication' and identifies Europe PMC as the resource. It distinguishes this tool from the sibling 'references' tool by explicitly framing it as forward citation tracking. The return fields (total citation count, title, authors, etc.) are also specified, leaving no ambiguity about the tool's function.

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 use cases: 'forward citation tracking, identifying follow-up research, measuring impact of specific papers, and discovering related work published after the original article.' This gives clear context for when to use the tool. It doesn't explicitly mention alternatives like 'references' for backward citations, but the forward-citation framing makes the distinction obvious enough. It could have been stronger with an explicit 'use references instead for backward citations' note, but the current guidance is solid.

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