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

Goes well beyond the annotations (which only declare read-only/idempotent/safe). It discloses the ranking algorithm (exact name, whole word, substring, all-words fallback), that the total match count is returned, that only an identical name counts as a warning-list match while similar names are reported separately for verification, and the important caveat that a negative result is not a compliance certificate.

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?

Purpose is front-loaded in the first clause and each subsequent sentence carries distinct information (matching order, match semantics, caveat). Sentences are long with stacked parentheticals, which slightly hurts scannability, but 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?

With no output schema, the description carries the return burden and does so adequately: it names the returned items (closest authorised entities and warning entries) and the total match count. Only minor gaps remain (no note on rate limits or result-size behavior) for what is otherwise a complete two-parameter read tool.

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 only 50% (top_k is undocumented in the schema), so the description must compensate. It explains top_k semantically ('returns the closest top_k ... entries') and adds case- and accent-insensitive matching for name, which the schema does not state. Bounds and defaults are left to the schema, which is acceptable.

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 two named resources (FINMA register of supervised institutions, FINMA warnings list) with the matching key (name). An agent can tell what it does, but the sibling tool 'finma_search' is not differentiated, leaving ambiguity about which FINMA search to pick.

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 a usage context ('Use it for basic counterparty screening') and a caution ('no result is not a compliance certificate'), which is useful framing. However it never states when to prefer this over the closely related 'finma_search' or any exclusions, so routing between siblings 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.