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

Discloses the full two-phase flow: the restaurant is not notified until the guest clicks the emailed link, the link expires in 24 hours, and the link is deliberately withheld from the agent. These are critical behavioral facts not derivable from the annotations, and they are consistent with readOnlyHint=false and destructiveHint=false.

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 core action and the most surprising fact (no notification yet), followed by operational instructions. The "request, not a confirmed booking" sentence partially restates the opening caps-lock warning, a small redundancy, but every other sentence carries non-obvious 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 7-parameter mutation with no output schema, the description covers the critical gaps: side effects, the out-of-band confirmation, link expiry, and why no confirmation handle is returned. It does not say what the tool actually returns on success (e.g. request id or pending status), leaving that to inference.

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 adds meaning by constraining email to "a real address belonging to the person you are acting for" and explaining that the confirmation link goes there and is not returned to the caller. It adds nothing about place_slug, requestedAt, or partySize beyond 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?

Opens with a specific verb+resource ("Request a table at a restaurant") and immediately scopes it against the confirmed-booking sibling by stating "This is a request, not a confirmed booking." An agent can distinguish it from create_booking without opening either 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 clear operating context: use the acting user's real email, tell them to check their inbox, link expires in 24 hours, and the restaurant confirms out of band. It never names create_booking explicitly as the alternative for a confirmed booking, so the routing is implied rather than spelled out.

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