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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds the key behavioral fact beyond them: "opens nothing by itself," clarifying that the return value is procedural guidance, not an action. It also notes there is no first-party MCP server and mentions the REST API alternative, explaining why a browser workflow is required. Return format is only loosely characterized, but no output schema exists to carry that.

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 point (what it returns, and that the browser tools do the actual work) is front-loaded. However, the main sentence is dense, packing the return type, the browser handoff, and the API footnote into one long clause. The "checked 23 Oct 2026" detail is tangential but does supply useful context for the API claim.

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 tool that returns instructions, the description covers purpose, the nature of the return value, and the required follow-up workflow. It does not explicitly say whether an authenticated Findymail account or Cloud Browser session is a prerequisite, a minor gap given the tool's simplicity and annotation coverage.

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?

There are zero parameters, so the baseline is 4. The description adds no parameter information because there is none to add.

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?

States a specific verb and resource ("Verify email in the user's own Findymail account") and distinguishes itself from siblings like findymail_find_email. The scope (own account, from an AI agent) is clear. It loses a point because the tool name and description imply performing verification, while the body reveals it actually returns instructions — a split that adds ambiguity.

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?

Explicitly describes the intended workflow: get the step-by-step instructions here, then execute them with cotlet_browser_* tools in the Findymail Cloud Browser. It does not state when not to use it or name alternatives for other Findymail tasks, but the sequencing guidance is clear enough for an agent to act on.

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