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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real substance beyond them: the return payload shape (screens, buttons, fields), the explicit non-side-effect guarantee ("opens nothing by itself"), and the required handoff to the browser tools. The closing note about Billetto's API v3 and the absence of an official MCP server is useful provenance but not behaviorally load-bearing.

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 operative sentences are tight and front-loaded enough to work, but the definition carries filler: "from ChatGPT, Claude or any AI agent" is promotional rather than informative, and the API v3 / no-MCP-server aside, while useful provenance, is not what an agent needs in order to call this tool. The purpose statement is also split awkwardly across the mutation-flavored opening and the clarifying second sentence.

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 input schema, no output schema, and full annotation coverage, the description covers the main gaps: it explains what comes back (step-by-step UI instructions) and how to act on it. It falls short of complete by not stating whether the user must be signed in or have a browser session open, and by not addressing how the relevant order is determined given the empty schema.

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 no parameters, so per the baseline there is nothing for the description to disambiguate and a 4 applies. That said, a zero-parameter tool whose object is a specific order note raises an implicit question (where does the order come from?) that the description does not address, which keeps it short of a 5.

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+resource ("Add order note") and then explicitly redefines the actual behavior: it "Returns how to do it in Billetto step by step (screens, buttons, fields) and opens nothing by itself." That correction is essential and distinguishes it from the cotlet_browser_* siblings that actually perform the click. It loses a point because the opening clause reads like a mutation and the reader must get three sentences in before learning the tool only returns guidance.

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 follow-up path: use the guidance returned here, "then do it with the cotlet_browser_* tools in the user's Billetto Cloud Browser." However, it never states prerequisites or when this tool should be preferred over directly driving the browser, and with zero parameters it never explains how the target order is identified (presumably from conversation context, but that is left to inference).

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