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

Goes well beyond the annotations (destructiveHint, openWorldHint, idempotentHint) by disclosing the concrete side effects: an email ~1 hour after a completed appointment, a next-day reminder, and a 3-day cutoff for stale appointments. This is exactly the kind of real-world impact an agent needs to judge before acting.

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?

Three tightly packed sentences: behavior first, default state second, risk warning last. No filler, and the safety-critical warning is front-loaded enough to be seen before the call is made.

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 mutating toggle with no output schema, the description covers trigger timing, default state, eligibility rules, and the user-confirmation requirement. Nothing an agent needs to invoke it safely 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 67% and the required `enabled` boolean has no schema description; the description compensates by defining what 'on' does (emails customers an hour after completion) and stating it is off by default, which pins down the boolean semantics. workspaceId and idempotencyKey are handled by 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 (turning appointment review requests on/off) and immediately distinguishes itself from review-handling siblings like reply_booking_review and set_booking_review_hidden by describing the automation it controls. An agent can tell what the tool does without opening the 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 operational context: off by default, and the explicit instruction to confirm with the user before turning it on because it emails real customers. It does not name a specific alternative tool, but the when-to-use caution is unambiguous.

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