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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them ('opens nothing by itself'). It adds genuinely useful behavior beyond the annotations: the return is procedural guidance in screens/buttons/fields, and the actual write must be performed through the cotlet_browser_* family. The closing note about Method CRM's REST API and the absence of an official MCP server does not describe this tool's behavior and is informational padding rather than transparency.

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 purpose is front-loaded, but the final sentence about the official REST API, the lack of an MCP server and the 'checked 23 Oct 2026' provenance is extraneous to selecting or invoking this tool. The middle sentence is densely packed, bending three ideas (returns steps, opens nothing, use browser tools) into one clause chain.

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 parameters, so the description carries the burden of explaining what comes back, and it does: step-by-step screens, buttons and fields. For an agent it is complete enough to know it must follow up with browser tools. It could be tighter about whether the guidance is text the agent relays or a checklist it executes.

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. The description does not wrongly imply inputs; notably it does not claim to accept estimate data, which correctly signals that the agent cannot pass record fields here and must supply them while driving the browser.

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 resource (an estimate in the user's Method CRM account) and, crucially, clarifies the actual function: it 'returns how to do it in Method CRM step by step (screens, buttons, fields) and opens nothing by itself.' That resolves the tension between the name 'create' and what really happens. It stops short of a crisp one-line 'this returns instructions, it does not create anything' framing, so the agent must piece the purpose together from two clauses.

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 execution path: use this to get step-by-step guidance, then 'do it with the cotlet_browser_* tools in the user's Method CRM Cloud Browser.' That names the alternative tool family and the condition selecting it. It does not state when NOT to use this (for example, if the user only wants a summary of the estimate fields) or what prerequisites the Cloud Browser needs.

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