api_request

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

Annotations already declare openWorldHint=true and destructiveHint=true, so the safety profile is known. The description adds genuinely useful routing behavior: path is resolved relative to the company unless it begins with /user, /info or /c/, which is non-obvious and would otherwise cause silent misrouting. It does not mention auth/scope requirements, pagination, or response/error handling for raw calls, so with annotations already covering the danger profile this lands at a solid 3.

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?

Two sentences, front-loaded with the scope definition before the path rules, with zero filler. The API reference URL earns its place as the escape hatch for everything the description cannot enumerate, though it slightly lengthens an otherwise tight definition.

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 raw passthrough with destructive and open-world annotations and no output schema, an agent needs to know path resolution, payload shape, and that responses are raw API JSON. Path resolution and a doc link are covered and the schema hints at the { data: {...} } envelope, but the raw response format and the undefined 'query' parameter are not addressed.

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 40%, so the description needs to compensate and it partly does: the path scoping rule (relative vs absolute prefixes) is the single most important semantic and is only in the description. However 'query' is undocumented in both description and schema, and 'method' semantics (which verbs mutate, which need bodies) are left entirely to inference, so compensation is incomplete.

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 (direct call to API v2) and defines its scope precisely as the fallback for anything without a dedicated tool, listing concrete example domains (settings, price lists, webhooks, pending documents). This makes it unambiguously distinguishable from every sibling, which are all named-resource CRUD tools.

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?

The phrase 'per tutto ciò che non ha un tool dedicato' gives a clear selection rule: use this only when no dedicated sibling exists. That implicitly excludes the ~80 named-resource tools. It stops short of explicitly telling the agent to prefer dedicated tools first, but the condition is stated plainly enough to act on.

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