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

Annotations already state readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, and the description reinforces this with 'opens nothing by itself', so there is no contradiction. It adds real value by describing the return content as a procedural guide and explaining that execution must happen through the browser tools, though it says nothing about whether the guidance is account-specific or static.

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 clarification ('returns how to do it… opens nothing by itself') is repeated twice in the first two sentences, and the trailing sentence about Method CRM's official REST API and MCP server status is vendor background rather than invocation guidance. The one genuinely useful constraint is not front-loaded.

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?

For a zero-parameter, read-only guidance tool with annotations covering the safety profile and no output schema, the description supplies what an agent needs: what comes back and which tool family performs the actual work. The omission of whether the steps are account- or invoice-specific is the main residual gap.

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 there is nothing for the description to disambiguate; the baseline applies. Note the agent cannot scope the guidance to a particular invoice or customer, which the description does not address.

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 eventually makes clear that the tool does not send anything but returns a step-by-step walkthrough (screens, buttons, fields), which contradicts the imperative name/title 'Send invoice'. That correction is present but buried after the leading sentence, and there is no differentiation from CRM siblings such as method_crm_convert_estimate_to_invoice or from cotlet_app_guide, so an agent must read carefully to know what it actually gets back.

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 an explicit usage flow: call this to get the procedure, then execute it with the cotlet_browser_* tools in the user's Cloud Browser, which is a clear hand-off to named alternatives. It lacks any when-not guidance (e.g., versus a direct CRM record tool) but the operative sequencing is unambiguous.

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