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

Given the annotations (readOnlyHint=true, openWorldHint=true), the description adds critical behavioral context: it only resolves PMC-indexed articles, imposes a batch limit, and requires a single ID type. These are non-obvious constraints that affect outcomes and are not derived from the annotations alone. It also names a concrete alternative for unsupported cases, increasing transparency about the tool's boundaries.

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 concise (two sentences) and front-loads the core purpose before diving into constraints and alternatives. Every clause earns its place: purpose, scope, batch limit, and redirection. No fluff or repetition, making it easy for an agent to parse quickly.

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?

With only two parameters and full schema documentation, the description covers all necessary behavioral context: what the tool does, its limitations (PMC-only, 50 IDs, single type), and when to use an alternative. The presence of an output schema covers return values. Nothing essential is missing for an agent to select and invoke this tool 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?

The schema already provides 100% coverage with detailed descriptions for both parameters, including examples and the optional 'PMC' prefix note. The description's statement about 'single type' and batch size largely reiterates the schema's maxItems and 'All IDs must be the same type.' While the description does add no harmful ambiguity, it provides minimal additional parameter-level meaning beyond what the schema already encodes.

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 begins with a clear verb-resource pair ('Convert between article identifiers (DOI, PMID, PMCID)') and immediately differentiates the tool from siblings by scoping to PMC-indexed articles. It also specifies batch limits and the single-type rule, making the tool's purpose unambiguous and distinct from sibling tools like pubmed_search_articles.

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 (for PMC-indexed articles) and when not to, naming the alternative: 'for articles not in PMC, use pubmed_search_articles instead.' It also mentions the 50-ID limit and the single-type requirement, providing clear usage context. This goes beyond a basic when-to-use and covers exclusions.

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