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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds the crucial context that resolves the apparent paradox of a 'create' tool being read-only: it only returns instructions and 'opens nothing by itself.' The note that TrueCoach has no public API further explains why a browser-driven guide is needed. It does not describe the exact return structure (number of steps, format), leaving a modest gap.

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 activation framing ('from ChatGPT, Claude or any AI agent') does little work, and the tool's real nature is buried mid-sentence after a misleading opening. The API footnote, including a future-dated '(checked 11 Oct 2026)', adds bulk. The core content is two useful sentences wrapped in filler.

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 output schema, the description carries the return-value burden and does so partially ('step by step (screens, buttons, fields)'). For a zero-parameter guide tool it covers purpose, side-effect profile, and the follow-up tool path adequately; only the precise shape of the returned guide is left unspecified.

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?

Zero parameters, so there is no schema semantics to supplement; baseline is 4. The description correctly implies no inputs are required, since the target is the user's own account and the target workout details are deferred to the browser step.

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 eventually makes clear that this tool does not create anything but returns a step-by-step guide ('Returns how to do it in TrueCoach step by step (screens, buttons, fields) and opens nothing by itself'). However, the leading sentence 'Create workout in the user's own TrueCoach account' reads as an action claim, so an agent skimming the first clause could misclassify it. The purpose is clear after full reading but is not front-loaded.

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 explicitly names the follow-on path: after getting the steps, 'do it with the cotlet_browser_* tools in the user's TrueCoach Cloud Browser.' That is a concrete when/how-to-use instruction. It stops short of stating exclusions or distinguishing this from cotlet_app_guide or truecoach_assign_program, so not a 5.

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