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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context about the result content: 'Jeder Treffer nennt Primär-, Stern- und Zusatzschlüsselnummer bereits mit ihrem amtlichen Titel...'. This goes beyond the structured metadata and sets expectations for what each hit will contain.

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 moderately sized and front-loaded with the core purpose, followed by usage conditions and alternatives. The German/English duplication repeats some content, but each sentence carries useful information and there is no filler.

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 search tool with an output schema, 100% parameter coverage, and readOnly/idempotent annotations, the description is largely complete: it gives purpose, when to use it, alternatives, and even describes the code types returned. The only minor gap is a slight tension between recommending icd10_search for known codes while the query parameter allows a code; this does not seriously impair completeness.

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%, so the schema already documents query, year, limit, and offset. The description adds the natural-language and partial-term use case with examples like 'Herz', 'Diabetes', 'Schmerz', but this supplements rather than replaces the schema. A baseline 3 is appropriate because the description does not need to compensate for missing parameter docs.

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 and resource: 'Durchsucht das Alphabetische Verzeichnis der ICD-10-GM' and explains it maps clinical/colloquial diagnosis terms to ICD-10-GM codes. It also explicitly distinguishes itself from icd10_search and icd10_get, so an agent can tell them apart 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?

Gives explicit when-to-use guidance: 'Best first tool for natural-language diagnosis search: use it when the user asks to find diagnoses by text, symptom, disease name, colloquial German wording or a partial term...'. It also names alternatives and the conditions for choosing them: use icd10_search when an ICD code is already known and icd10_get for the full entry of one code.

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