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

Annotations already declare this is a non-read-only, non-idempotent, open-world mutation, so the safety profile is covered. The description adds genuinely new context beyond them: the code must come from verify_my_phone, the operation is one-time, and the result persists into later bookings.

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?

Two short sentences, the action and its required input front-loaded, then the frequency/persistence note. No filler.

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?

There is no output schema and no annotations describing results, so the description should cover outcomes: what a success or failure looks like, whether the code expires, and the expected phone format. It covers the prerequisite and persistence model but leaves these gaps.

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 0%, so the description carries the burden, and it clarifies the code parameter with a format constraint (6 digits) and its source. The phone parameter is left undefined – no format, E.164, or whether it must match the number passed to verify_my_phone.

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 concrete verb and resource (confirm the client's mobile number) and identifies the exact input artifact (the 6-digit code from verify_my_phone). It is clearly separable from its sibling verify_my_phone, which initiates the flow rather than completing it.

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?

"Needed once; later bookings reuse it" tells the agent when this step is required and that it should not be repeated, and it points at the prerequisite tool verify_my_phone. It stops short of naming an explicit alternative or stating what to do if confirmation fails or the code expires.

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