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

The description goes well beyond the annotations by disclosing that the tool opens nothing by itself and only returns instructions, which explains why readOnlyHint=true sits on a tool named 'book'. It also names the required execution environment (user's OpenTable Cloud Browser) and the API-access constraint, giving the agent everything needed to avoid assuming a booking occurred.

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 critical qualifier (opens nothing by itself) is front-loaded in the first sentence, which prevents a costly misinterpretation. The phrasing is slightly awkward, with the semicolon-joined 'then do it with...' clause and the trailing API note feeling tacked on, but nearly every sentence carries useful 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?

With no output schema, the description carries the burden of describing return values and does so concretely: a step-by-step guide covering screens, buttons, and fields. It also supplies the follow-up action required to complete the task, so an agent has no missing links between this call and a finished booking.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. It correctly avoids inventing parameter detail and instead explains where the reservation details come from (the step-by-step output and subsequent browser actions).

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 states a specific verb and resource (book a reservation in the user's OpenTable account) and immediately clarifies the tool's actual output: step-by-step instructions with screens, buttons, and fields. It explicitly distinguishes itself from the cotlet_browser_* siblings by naming them as the tools that perform the actual 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?

It gives a clear usage path: call this tool to get the walkthrough, then execute it with the cotlet_browser_* tools in the OpenTable Cloud Browser. It also preempts the obvious alternative route by noting OpenTable has no public API for non-partners. There is no explicit statement of when NOT to use it versus cotlet_app_guide, but the context is otherwise unambiguous.

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