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

Beyond the annotations, it discloses that the reply originates from the partner (openWorldHint is confirmed, not repeated), warns that the response is untrusted data whose embedded instructions must not be followed, and clarifies that payment happens outside Foundaree. It does not warn that repeated calls of a non-idempotent action can duplicate a booking or order, which is the main residual risk.

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-loaded with the action, then the discovery path, then the safety constraints; nearly every sentence carries distinct information. The opening sentence is long and parenthetical-heavy, which slows scanning slightly.

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?

Covers discovery, invocation, consent, and trust handling of the external response, which is strong for an open-world, non-idempotent tool with no output schema. It stops short of describing failure behavior (unknown slug or operation) or the duplicate-action hazard, which an agent would still need to infer.

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 3 is the floor. The description adds real constraint beyond the schema by saying `input` must contain exactly those fields and that `app` is the slug and `operation` the name obtained from `get`, which anchors where each value comes from.

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: calling a single operation of a partner mini app, with the domain examples (cab company, delivery app, shop). It also explicitly positions itself relative to siblings by naming `find` (lists mini apps) and `get` (shows each operation and its fields) as the discovery path.

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 the exact workflow: use `find` to get the slug, `get` to see operations and fields, then call with `app`/`operation`/`input`. It also states a hard precondition for the most dangerous case — kind "action" operations require the user's account to be connected and the user's explicit yes.

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