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

Annotations already declare readOnly, non-destructive, idempotent, not-open-world, so the safety profile is covered; the description still adds real context beyond that: it produces step-by-step screen/button/field instructions, has no side effects ('opens nothing by itself'), and requires a follow-up execution path via cotlet_browser_*. The API access constraint is useful context an agent would otherwise waste a turn discovering. It does not say anything about account permissions or what happens if no client context exists, which is why it isn't a 5.

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?

Three sentences, front-loaded with the action and the critical 'opens nothing by itself' qualifier before the follow-up tooling. Every sentence carries information, though the trailing API paragraph with the '(checked 11 Oct 2026)' date is somewhat tangential to a step-by-step guidance tool and adds length without changing what the agent does.

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 and no output schema, the description carries the burden of describing the return value, and it does: step-by-step Everfit screens, buttons, and fields. It also closes the loop on the next action (cotlet_browser_* in the Cloud Browser) and rules out the API, which is everything an agent needs to call this correctly.

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 per the baseline this dimension starts at 4. There is no argument surface for the description to clarify, and it correctly implies that all context (account, client) comes from the caller's session rather than from inputs. Minor ambiguity remains about how the target client is identified given an empty schema, but that is not a parameter-semantics failure.

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 resource and verb ('message client in the user's own Everfit account') and immediately disambiguates the kind of action by stating it 'Returns how to do it in Everfit step by step ... and opens nothing by itself.' That tells an agent this is a guidance/instruction tool rather than an executor, which separates it from the cotlet_browser_* siblings. The only friction is that the name/title implies a direct messaging action, which the body has to walk back.

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?

Explicit routing is given: get the steps here, 'then do it with the cotlet_browser_* tools in the user's Everfit Cloud Browser.' It also pre-empts the obvious alternative (the official API) and explains it is Enterprise-only, so the agent won't stall looking for an API path. It does not state exclusions relative to the other everfit_* siblings (e.g. when to use assign_program instead), so it stops short of full when/when-not coverage.

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