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

Beyond readOnlyHint/idempotentHint, the description usefully discloses that the tool "opens nothing by itself" and that the actual action must be performed through browser tools. That is exactly the side-effect context an agent needs and matches the annotations. It stops short of describing the shape of the returned instructions or what happens if the Cloud Browser isn't open.

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 core statement (returns instructions, opens nothing, use browser tools) is good, but it is buried after a misleading opening clause. The trailing digression about Breezeway's REST API, key request forms, and an MCP-server check date is peripheral to invoking this tool.

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 and no output schema, the description should fully explain what the returned guidance looks like and the handoff to the browser tools. It gestures at "screens, buttons, fields" but does not describe the output structure or prerequisites such as having a Breezeway Cloud Browser session open.

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 schema burden is nil and the baseline is 4. There is nothing the description could add about inputs.

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 first sentence reads as if it fetches people ("List people in the user's own Breezeway account"), and only the second sentence reveals the real behavior: it returns step-by-step UI instructions. The name and title reinforce the misleading reading, so an agent must parse the whole description to learn this tool returns guidance, not data. It is ultimately resolvable, but not cleanly stated.

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 does give a follow-up path ("then do it with the cotlet_browser_* tools in the user's Breezeway Cloud Browser") and notes the official API needs keys and has no MCP server. But it never says when to pick this versus siblings like breezeway_list_properties/tasks or cotlet_app_guide, and offers no explicit exclusions.

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