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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false), so the description's extra disclosure counts: results arrive in 'items' as complete catalog rows with the full coding-flag set (Alters-/Geschlechtsbezug, CCL, Chroniker, IfSG-Meldepflicht, Morbi-RSA, DKR-/SEG-4-Verweise). It also states what the tool does NOT return (per-code Inklusiva/Eklusiva/Kodierhinweise) and routes to icd10_get. Not a 5 because search-matching behavior (partial-kode matches, ordering, case handling) is not disclosed — a miner gap given the output schema documents return shape.

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?

Core capability is front-loaded in the first sentence and usage routing comes last, which is well ordered. However, the bilingual German/English format repeats the search capability and result-content points in both languages, so a substantial share of the text is redundant; each language half is tight on its own, but combined, not every sentence earns its place.

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 medium-complexity search tool in a large domain family (25 siblings spanning ICD-10, alpha catalogs, OP S, DRG, ATC, and more), the description resolves the critical routing decisions: systematic-vs-alphabetal search, code-vs-free-text input, and single-code follow-up — and states exactly what the returned rows contain. With annotations covering safety and an output schema covering return values, 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?

Schema description coverage is 100% — year, limit, and query each carry their own descriptions with concrete examples ('E11', 'E11.0', 'Diabetes mellitus Typ 2'), so the schema does the heavy lifting. The description re-states that query may be a code or diagnosis text but adds no parameter-level syntax or format detail beyond the schema. Baseline 3 applies when schema coverage is high.

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+resource: 'Durchsucht den ICD-10-GM (amtlicher Diagnoseschlüssel) nach Kode oder Diagnosetext' — searches the ICD-10-GM catalog by code or diagnosis text. It also distinguishes itself from the closest siblings by name: icd10alpha_search for natural-language wording and icd10_get for single-code details. An agent can tell this tool apart without opening any schema.

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 routing: 'Use this when an ICD code is already known or systematic rows are wanted; when the user only has natural-language wording... call icd10alpha_search first', and names the follow-up protocol for per-code details ('Für Inklusiva, Eklusiva und Kodierhinweise... anschließend icd10_get aufrufen'). Both when-to-use and when-not-to-use are spelled out with named alternatives — exactly what is needed in a 25-tool sibling family.

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