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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety bar is low; the description still adds real value by stating explicitly that it 'opens nothing by itself' and that the actual work must be delegated to browser tools. The API-availability note (Faire has a partial External API with per-brand tokens) is relevant context about why browser automation is needed. It does not contradict, and usefully reinforces, the read-only annotation.

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 behavioral core is front-loaded and clear, but the opening audience clause ('from ChatGPT, Claude or any AI agent') is marketing filler that does not help an agent act. The trailing API paragraph with a dated verification stamp ('checked 11 Oct 2026') is tangential to invoking the tool and dilutes an otherwise short 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, no-output-schema guidance tool whose annotations cover the safety profile, the definition supplies what an agent needs: what it returns (screens, buttons, fields), that it performs no action, and the follow-up tool family to use. The only residual gap is that it never says how the returned steps relate to a specific account section or what to do if a step fails.

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 no inputs are needed, since it simply returns a procedure.

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 concrete resource (orders in the user's own Faire account) but immediately reframes the tool as something else: 'Returns how to do it in Faire step by step (screens, buttons, fields) and opens nothing by itself.' So the name suggests fetching data while the description says it returns instructions. An agent can eventually work out it is a guidance tool, but the verb/resource pair is internally inconsistent and it is not distinguished from the sibling cotlet_app_guide.

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 usable workflow signal: read the returned steps, then execute them with the cotlet_browser_* tools inside the user's Faire Cloud Browser. What is missing is any statement of when NOT to use it, or why an agent would pick this over the similarly-scoped cotlet_app_guide for Faire procedures.

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