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

With no annotations, the description fully discloses the tool's side effects: the restaurant is not notified yet, a confirmation email is sent, the link expires in 24 hours, and the link is deliberately not returned to the agent. This is rich behavioral context beyond what the schema conveys.

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?

The description is appropriately sized for the tool's complexity. It front-loads the primary purpose, then delivers critical behavioral warnings in a logical sequence. Every sentence earns its place, avoiding redundancy.

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?

Given the tool's multi-step behavior (request held, email sent, link click required, restaurant confirms out of band), the description covers all necessary context. There is no output schema, but the description explicitly states that no confirmation is returned to the agent, setting correct expectations for the return value and follow-up.

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 meaningful context for the 'email' parameter by explaining it must belong to the person being represented and that the confirmation link is sent there, which clarifies why this parameter is essential. Other parameters are adequately documented in the schema, so the description need not repeat them.

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?

The description clearly states the tool requests a table at a restaurant, using a specific verb and resource. It explicitly distinguishes itself from a confirmed booking ('This is a request, not a confirmed booking'), which differentiates it from sibling tools like create_booking.

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?

Provides explicit usage context: the request is held and not sent to the restaurant until the confirmation link is clicked. It advises the agent to tell the user to check their inbox and to use a real address of the person being represented. It also clarifies when not to treat it as a confirmed booking, offering an alternative path ('confirms out of band').

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