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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial context beyond them: the per-IP daily call cap shared across three tools, the remaining-calls reporting, the FINMA data version disclosure, and the ranked match_type output. These are behavioral traits an agent cannot derive from structured fields.

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 the trial constraint and verification warning before the search mechanics, which is the right priority. It is dense but each sentence carries distinct information (quota, verification, tolerance, ranking order, warnings toggle, data version); only the ranking enumeration risks feeling list-heavy.

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 must convey return shape, and it partly does: ranked results labelled with match_type, remaining trial calls, and the FINMA data version. That is fairly complete for a search tool, though it does not describe result payload fields or pagination.

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 67% (name and include_warnings documented; top_k undocumented). The description reinforces name tolerance and include_warnings behavior, adding meaning about how matching works, though it does not clarify top_k beyond the schema's default and range.

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 ('Search the FINMA register by entity name') and details the tolerance semantics (case, accents, legal forms, ae/oe/ue, typos). It distinguishes itself from siblings by naming classify_text and tariff_semantic_search in the shared trial quota, and it is clearly not kyc_check or cross_walk.

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 clear context: free trial without a key, 20 calls/day shared across three named tools, and a verification directive ('check every result on the official FINMA register before use'). It also flags include_warnings as an opt-in behavior. However it never states when to choose finma_search over kyc_check or cross_walk, so alternative selection is left to inference.

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