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

Annotations only declare the mutation shape (readOnlyHint=false, openWorldHint=true, idempotentHint=false); the description supplies the real behavioral context an agent needs: the recipient sees the request on Foundaree and calls back, nothing is confirmed until then, and payment happens directly between the parties. It also discloses the return value (`bookingId`) and the verification path via `check`, which annotations cannot express.

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?

Dense but front-loaded: purpose and examples come first, then preconditions, confirmation gate, behavioral outcome, and return value in a logical order. Minor redundancy in "only with the user's OWN name and phone number, which they gave you: never guess or reuse another number" costs a point but every sentence is actionable.

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 9-parameter outbound request tool with no output schema, the description covers the confirmation flow, the asynchronous acceptance model, payment boundaries, and what is returned. Nothing an agent needs to call it safely and correctly is missing.

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 the baseline is 3; the description still adds provenance and constraints the schema doesn't, namely that `kind` and `username` come from a prior `find` result and that `name`/`phone` must be the user's own supplied values, never reused. It stops short of clarifying optional fields like `area` or `items` any further.

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?

Opens with a specific verb and resource ("Send a booking or order to one person or business on Foundaree") and backs it with three concrete user-utterance examples. It also distinguishes itself from sibling tools by pointing to `find` as the source of `kind`/`username` and to `check` as the follow-up step.

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 explicit when-to-use ("only when the user asked to book"), a hard precondition ("A business must have `bookable: true`"), and a required confirmation gate ("tell the user what you will send and to whom, and get their yes"). It also names when not to proceed by prohibiting guessed or reused phone numbers.

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