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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: it discloses that the tool performs no UI action itself, that its output is a screen/button/field walkthrough, and that the follow-up execution happens through cotlet_browser_* — none of which is inferable from annotations.

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?

Purpose and the critical 'this does not execute anything' caveat are front-loaded in the first sentence, which is good structure. The closing API-investigation sentence is longer than needed for the information it carries, though it does justify why browser automation is the path; trimming it would improve the definition.

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 helper the description covers purpose, return content, and the follow-up mechanism, which is close to complete. Minor gaps: it does not state the output format (prose vs structured steps) or prerequisites such as an existing Cloud Browser session for the user; the stated API-research date of 11 Nov 2026 also reads as a future/placeholder date that could confuse an agent.

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 input parameters, so the baseline is 4 and there is nothing further the description could usefully add. The description correctly implies no arguments are needed by framing the tool as a pure instruction lookup.

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 names a specific verb and resource ("Export payments") and, unusually, clarifies the deliverable: it returns step-by-step instructions rather than performing the export, explicitly stating it "opens nothing by itself." It does not name the sibling export tools (export_customers, export_statements, export_report) to differentiate scope, but the payments focus is unambiguous.

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 usage path: call this to get the procedure, then execute it with the cotlet_browser_* tools in the user's Cloud Browser. That is actionable guidance an agent can follow. It stops short of stating exclusions (e.g., when to prefer a direct API path or a different export sibling), so it is clear context without true when-not guidance.

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