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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is known; the description then adds genuinely new behavior: the confirmation is one-time and expires after 10 minutes, which explains the non-idempotent, non-read-only flags. It also imposes a response-handling obligation (surface serviceAnnouncements distinctly), though it doesn't say what the preview returns or how the token is carried forward.

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 action and confirmation/expiry constraint are front-loaded in the first sentence, with presentational and announcement instructions following in logical order. Three sentences with no redundancy, though the Geekist operator phrasing is more verbose than the point requires.

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 and a complex nested input, the description covers the user-facing workflow but omits what a preview actually yields and whether a returned token/reference must be handed to the create step. For a tool whose whole purpose is to gate a subsequent call, that handoff detail matters and is left implicit.

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?

Schema description coverage is 0% and the single parameter is a deeply nested workout object with required name/sport/steps, an anyOf array of step types, repeat blocks, and four mutually exclusive target shapes (pace min/km, heart-rate bpm, HR zone, power watts). The description adds no structural guidance beyond the phrase 'targets and units', which is about display rather than input construction, leaving an agent to reverse-engineer the nested schema unaided.

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 and resource ('Preview a proposed running or cycling workout') and immediately scopes the follow-on action ('prepare a one-time confirmation ... before creation'). This distinguishes it from garmin_create_workout and the read-only garmin_get_workout sibling without the agent needing to open another schema.

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 workflow condition clearly: preview first, show intervals/targets/units to the user, and only then confirm before creation. What's missing is an explicit exclusion naming the alternative (e.g. 'call garmin_create_workout after confirmation'), but the sequencing intent is unambiguous.

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