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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds valuable behavioral detail: results appear in 'items' as complete catalog rows with multiple listed coding flags (age/sex, CCL, chronic, IfSG, Morbi-RSA, DKR/SEG-4). No contradiction with annotations. It does not over-disclose or need to cover mutating concerns because the tool is read-only.

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 text is front-loaded with the core search purpose and adds sibling routing at the end. It is slightly longer than necessary because the German and English portions partly duplicate the search statement, but every major piece of guidance (result contents, follow-up tool, alternative tool) is present and no filler remains.

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 read-only search tool with an output schema, the description is complete: it explains what the results contain, when to use this tool, when to use the alpha alternative, and how to get single-code detail. The schema covers the parameters and the output schema covers return structure, so nothing needed for correct invocation is missing.

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?

Input schema description coverage is 100%, so the schema already documents query, year, and limit. The description only restates that query can be a code or diagnosis text, and the schema already supplies examples like 'E11' and 'Diabetes mellitus Typ 2'. Thus the description adds no significant parameter-level meaning beyond the structured definitions.

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 names a specific action ('Durchsucht den ICD-10-GM') and a concrete resource, and clarifies how it differs from siblings: it returns full systematic catalog rows and explicitly points to icd10_get for single-code details and icd10alpha_search for natural-language diagnosis wording. This makes the tool distinguishable from nearby search/get tools without opening schemas.

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?

It gives explicit routing: use this when an ICD code is already known or systematic rows are wanted; for natural-language wording, call icd10alpha_search first; for inclusions/exclusions/coding notes of a single code, call icd10_get. This is a direct when/when-not statement with named alternatives.

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