garmin_create_workout

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

Annotations give only readOnlyHint=false and destructiveHint=false, so the description carries the responsibility for explaining real-world effects. It does this by noting optional scheduling and that 'Once scheduled it appears on the watch on that date,' plus the ordered and repeatable nature of steps. This is meaningful behavioral context and does not contradict the annotations.

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 description is front-loaded with the tool's purpose, then moves into a compact but sufficiently detailed explanation of the step grammar. The nested-repeat example is instructive rather than filler, and the final sentence about the watch appearance adds useful behavioral context. Every sentence earns its place.

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 mutating tool with a complex nested `steps` parameter, the description is close to complete: it defines valid step kinds, length formats, pace formats, heart rate zones, notes, and repeat nesting. The main noticeable gap is the lack of an explicit `schedule_date` format, and `name`/`description` receive no dedicated explanation. Since an output schema exists, the absence of return-value details is acceptable.

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?

With schema_description_coverage at 0%, the description compensates strongly by fully explaining the hardest parameter, `steps`, including `kind`, `length`, `pace`, `heart_rate_zone`, `note`, and nested repeats. It also hints at `schedule_date` through 'optionally scheduling it' and 'that date.' However, it does not specify the expected date format or explicitly describe `name` and `description`, leaving some minor gaps.

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 clearly states the tool's action: 'Create a structured running workout on Garmin, optionally scheduling it.' It identifies the resource and even describes the step structure, making the core purpose obvious. It does not explicitly contrast itself with the sibling garmin_schedule_workout, but the create-versus-schedule distinction is largely inferable from the naming and first sentence.

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?

The description explains the mechanics of building workout steps but never states when to prefer this tool over alternatives like garmin_schedule_workout or garmin_list_workouts. It provides no conditions, exclusions, prerequisites, or explicit routing guidance. The only usage signal is the implied act of creating a new workout, which is minimal guidance for an agent choosing among many siblings.

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