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

Beyond the annotations, it discloses the crucial behavioral fact that the tool performs no action of its own and only returns procedural guidance, and that the real work happens in the Cloud Browser. This is exactly the kind of context annotations cannot convey. The trailing note about the Connector API adds no behavioral information.

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 operative fact (this returns instructions, it does not act) is placed second, behind an audience-boilerplate clause naming ChatGPT and Claude. The closing sentence about Mews's official Connector API and the absence of an MCP server is irrelevant to invoking the tool and does not earn its place.

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 parameters, no output schema and generous annotations, the description covers what an agent needs: what comes back, that nothing is mutated, and which tool family to use next. It could go slightly further in describing the shape or scope of the returned steps, but nothing essential 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?

The tool takes zero parameters and the schema is an empty closed object, so there is no parameter semantics to explain and none are misrepresented. Baseline of 4 applies for a no-parameter tool.

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 does state concretely what the tool returns: step-by-step Mews instructions covering screens, buttons and fields, plus an explicit disclaimer that it opens nothing. The verb in the lead sentence and tool name ("search reservations") points the opposite way from the actual behavior (returns guidance, not reservation records), which costs it a point but the purpose is resolvable.

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 workflow handoff: read the guidance here, then execute with the cotlet_browser_* tools in the user's Mews Cloud Browser. However it never distinguishes this from data-returning siblings like mews_list_arrivals or mews_list_departures, so an agent has no basis for choosing between them.

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