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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'opens nothing by itself', so there is no contradiction. It adds context the annotations cannot convey: the return format (ordered steps with screens, buttons, fields) and the authentication reality of FieldEdge's API being gated behind an onboarding request. Rate limits and failure modes of the browser handoff are not covered.

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 critical behavioral fact ('opens nothing by itself') is placed well, but the lead-in 'from ChatGPT, Claude or any AI agent' is filler, and the closing paragraph on FieldEdge's API policy is longer than needed to make the point that no API shortcut exists. The description is serviceable but not tight.

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 carries the burden of explaining what comes back, and it does so by specifying step-by-step screen/button/field guidance plus the follow-on browser tools. An agent has enough to know what this call yields and what to do next; only the handoff mechanics between this tool and cotlet_browser_open are left implicit.

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 and the baseline of 4 applies. The description correctly implies the invoice target is supplied later through the browser tool calls rather than as an argument, which prevents an agent from hunting for a missing input.

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 makes the key distinction explicit: the tool does not send anything itself, it 'Returns how to do it in FieldEdge step by step (screens, buttons, fields)'. That resolves the ambiguity created by the imperative name 'send_invoice' and tells an agent this is a guidance-producing tool. It stops short of a single crisp verb+resource statement up front (the opening sentence reads like a marketing line about AI agents), which keeps it out of the top band.

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 concrete workflow: call this first, then perform the actual steps with the cotlet_browser_* tools in the user's FieldEdge Cloud Browser. It also explains why the official API is not an option (access only on request via FieldEdge's onboarding form). It does not address when to prefer this over the sibling cotlet_app_guide, so the alternative-selection guidance is incomplete.

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