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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false), so the description's key contribution is the non-obvious disclosure that the tool performs no action itself and instead returns step-by-step instructions. That is exactly the kind of behavioral context an agent needs, though the description never states the return shape concretely (text vs. structured steps).

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 text is padded with marketing framing ('from ChatGPT, Claude or any AI agent') and a trailing note about Intervals.icu having an official public REST API 'checked 6 Nov 2026' that has no bearing on how to call this tool. The genuinely useful content — that it returns a UI walkthrough and does not act — is buried in a run-on 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 parameters and no output schema, the description must fully explain what comes back; it names 'screens, buttons, fields' as the content and points to the cotlet_browser_* tools as the follow-up, which is adequate. It still leaves the scope of 'sport settings' and the exact return format vague, and the name/behavior mismatch could mislead an agent.

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. Baseline of 4 applies; nothing about the empty schema is misrepresented.

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 name and first sentence promise 'get sport settings', but the second sentence says the tool 'Returns how to do it in Intervals.icu step by step (screens, buttons, fields)', i.e. it returns an instructional guide rather than the settings themselves. An agent cannot cleanly tell whether this is a data-fetch tool or a how-to-guide tool, though the contrast with the cotlet_browser_* tools that actually perform the action does hint at its role.

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?

There is usable guidance: 'opens nothing by itself; then do it with the cotlet_browser_* tools', which tells the agent this is a preparatory step followed by browser actions. However, no guidance is given on when to choose this over the other intervals_icu_* read tools or what to do if the user already knows the UI.

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