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

Annotations only declare readOnlyHint and openWorldHint, so the description usefully adds that data comes from USPTO and conditionally EPO ('when configured'), and that 'Missing text is omitted rather than filled in' — important partial-result behavior for an agent. It omits error/not-found handling and any rate-limit or latency context.

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?

Three short sentences, front-loaded with the retrieval scope and sources, followed by the omission caveat and disclaimer. No filler; every sentence carries distinct information.

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 no output schema, the description correctly states what is returned and notes that missing fields are dropped, which is the key detail for parsing. It could still say what happens on an unknown/invalid number, but for a one-parameter lookup it is largely 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?

Schema description coverage is 100% and the single parameter documents accepted formats (US12000000, 12000000, EP0351918) plus length bounds. The description adds no further format or normalization guidance, so the 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 gives a specific verb ('Fetch') and resource ('one patent') and enumerates the returned fields (title, abstract, claims, status, family, citations). The singular scope implicitly separates it from search_patents and search_prior_art, but no sibling is named explicitly, and the inclusion of citations slightly overlaps find_patent_citations without clarification.

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?

Usage is only implied: the tool takes a single patent number and returns one record's details, so an agent can infer it is for retrieving a known patent rather than discovering patents. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., search_patents for discovery, find_patent_citations for citation graphs).

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