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

Annotations already indicate read-only, idempotent, open-world behavior. The description adds meaningful behavioral detail beyond annotations: results are ordered 'most recent first', and the citation count is a 'FLOOR' due to PubMed Central coverage limits.

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 front-loaded with the core purpose and each sentence adds useful information: usage, use cases, caveat, and sibling distinction. It is slightly long but not padded.

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 two-parameter tool with no output schema, the description adequately explains inputs, return behavior ('returns citing papers... with full citation metadata'), ordering, limitations, and relationship to related tools.

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%: both pmid and limit are documented with types and defaults. The description adds only 'Pass one PMID', which is redundant with the schema, so it stays at the baseline for high coverage.

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?

Description uses a specific verb and resource: 'Find papers that CITE a given article — forward citation search.' It clearly differentiates from the sibling tool by stating 'Distinct from pubmed_get_related_articles (similar papers, not 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?

Explicitly tells the agent how to call it: 'Pass one PMID', what results to expect, when to use it ('who cited this', 'has this finding been replicated or challenged'), and even points to alternatives for broader citation coverage (Semantic Scholar / OpenAlex).

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