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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real nuance — diacritics are optional in queries and JGP groups are always resolved against today's catalog. The latter is a meaningful behavioral quirk an agent wouldn't infer from the schema, though it sits in slight tension with service_date 'picks the release in force'.

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?

Two dense sentences with no filler; the searchable scope is front-loaded and the follow-up routing is compactly appended. Every clause carries 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 an output schema present, the description needn't document return shape — yet it briefly previews hit contents (code, title, path, JGP group count), which is a bonus. Safety profile, scope, and next-step tools are all covered for a four-parameter search.

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 baseline is 3. The description still adds meaning beyond it: query accepts either a code or Polish words with optional diacritics, and systems should include icd11-pl only on request — guidance the enum alone does not convey.

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 (Search) and enumerates the exact resources covered: ICD-10 PL diagnoses, ICD-9 PL procedures, JGP groups, and pre-released ICD-11 PL. It also distinguishes itself from siblings by naming get_code, get_jgp_group, and browse_codes as the follow-up/navigation tools.

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?

Clear routing guidance: open a hit with get_code or get_jgp_group, walk a hierarchy with browse_codes, and add icd11-pl 'only when asked'. The condition for the ICD-11 dictionary is explicit. It lacks a direct statement of when search is the wrong entry point versus browsing, but the alternatives are named and contextualized.

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