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', which is consistent. It adds two useful behaviors beyond annotations: the return is a step-by-step guide with screens/buttons/fields, and the official API path is unavailable to ordinary users. It stops short of describing the guide's size, format, or what the agent should do if the guide does not match the live UI.

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 behavior and the handoff to cotlet_browser_* are front-loaded and clear. However, the sentence runs together several concerns, and 'from ChatGPT, Claude or any AI agent' plus the timestamped API aside ('checked 10 Oct 2026') add length without helping an agent decide or act. The API note earns partial credit as a rationale for why the browser path is required.

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, non-mutating guide tool with no output schema, the description covers the essentials: what comes back, that nothing is executed, and which tools to use next. It is thin on the cross-tool contract, though — it does not say whether the guide must be read before calling cotlet_browser_* tools or what to do if the Everfit UI differs from the returned steps. Adequate but with clear gaps.

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 and the schema is closed, so there is no parameter meaning to convey. Baseline 4 applies; nothing in the description is needed or wasted on parameters.

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 the specific resource (body metrics) and account (the user's own Everfit), and explicitly corrects the expectation set by the name: it 'Returns how to do it in Everfit step by step' and 'opens nothing by itself'. That makes clear this is an instruction-provider rather than a data reader, which is the key distinction an agent needs. It does not distinguish itself by name from cotlet_app_guide, but the verb+resource framing is otherwise specific.

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 states the follow-on step explicitly: 'then do it with the cotlet_browser_* tools in the user's Everfit Cloud Browser', giving an actionable workflow rather than a dead end. It also rules out the API path by noting it is Enterprise-only and requires emailing for a token. What it does not state is the precondition (browser already open/navigated) or when to prefer cotlet_app_guide over this tool.

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