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

Annotations declare idempotentHint=true, but the description goes well beyond them by spelling out the exact idempotency semantics: same key or same data returns the same booking, and the token is only re-issued with the same idempotency_key. It also discloses a real side effect the annotations don't capture — the company messages the client on WhatsApp or e-mail — and states the return values.

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 and its prerequisites, and nearly every sentence carries information. The final idempotency/retry sentence is long and clause-dense, which costs a little readability, but nothing is genuinely redundant.

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 14-parameter mutation with a nested `diagnosis` object and no output schema, the description covers the missing pieces: it explains the return (request number + status token), the chain of prerequisite calls, and the retry contract. Nothing an agent needs to invoke or recover from this call is absent.

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 already 93%, so most parameters are self-documenting and the baseline is 3. The description still adds genuine meaning on top: it explains what `company` must be sourced from, why to send an `idempotency_key`, and how email vs. WhatsApp delivery is selected. It stops short of touching the less obvious params like district, units, and answers, leaving those entirely to the schema.

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 ("Books the visit") and anchors both inputs to their producing siblings (company from find_companies, slot from check_availability). An agent can distinguish this from get_quote, diagnose, and check_availability without opening any schema.

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 an explicit precondition chain — only after the client confirmed the service, time, address and price — and names the sibling calls that must precede it. It also names the downstream tools (get_request_status, cancel_request) whose token this returns, which routes the agent forward.

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