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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real behavioral context: full claims/description text is reliably present only for granted (B-kind) and directly-filed applications, Euro-PCT entries return only the bibliographic record, and the response signals which case occurred instead of returning empty. That last point is valuable disclosure about return 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?

Front-loads purpose in the first clause, then parameter guidance, then the important Euro-PCT caveat. It is dense but each sentence carries weight; slightly long, but the complexity of the kind/PCT behavior justifies most of the length.

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 still tells the agent what it will receive (biblio/abstract/claims/description, and that the response reports whether full text was available). Combined with complete schema coverage and annotations, an agent has everything needed to invoke and interpret the call 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it explains the full-id vs bare-number-plus-kind relationship, recommends the full id, and ties the reliability of claims/description output to the patent kind. This is genuine added semantics rather than restatement.

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?

States a specific verb (Fetch) and resource (one EP patent publication as published by the EPO) with the exact scope of what can be retrieved (bibliographic data, abstract, claims, description). This clearly distinguishes it from the sibling eps_list_publications, which enumerates rather than fetches a single record.

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?

Gives concrete guidance on how to call it — pass a full id from eps_list_publications (recommended) or a bare number plus kind — and names the sibling that supplies ids. It does not spell out explicit when-not-to-use exclusions, but the usage context is clear and actionable.

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