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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the description is not carrying the safety burden alone. It still adds real value beyond them: how path parameters are bound by name (:protocol → params.protocol), how remaining params become query string vs. JSON body for POST, and that api_key is only needed for keyed operations. Note the destructiveHint=false annotation is a bit optimistic for a tool that can POST to arbitrary operations, but the description does not directly contradict it.

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?

Three tight sentences, no filler. The core purpose is front-loaded, and the discovery hint, param-mapping rule, and auth note each carry distinct, non-redundant information.

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 no-output-schema generic dispatcher, the description covers discovery, param binding, method/body routing, and auth, which is most of what an agent needs to invoke it correctly. The one notable omission is explicit guidance on when to prefer this tool over the operation-specific siblings.

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 100%, so baseline is 3, and the description earns above that by explaining cross-parameter mechanics the schema cannot: the name-based binding of params to path segments, the query-string vs. body routing, the GET default for method, and the keyless-read/keyed-write split for api_key. It adds genuine semantics on top of the per-field schema text.

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: 'Call any public operation of the coordination API by its /v1 name'. This clearly identifies it as a generic dispatcher, which is distinct in kind from the operation-specific siblings. However, it never explicitly says how it relates to the 14 named siblings (taifoon_buy, taifoon_sell, etc.), leaving the agent to infer when the generic path is preferable.

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 tells the agent how to discover valid operation names (GET /v1/ops/search, GET /v1/openapi.json), which is useful procedural guidance. But it gives no rule for choosing this generic tool over the dedicated sibling tools that presumably wrap the same operations, so usage is only implied.

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