create_course

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

Beyond the annotations (which only declare write/non-destructive/open-world), the description discloses substantially more: validation occurs before any request (empty name or fewer than two geoPoints throws GarminError), Garmin computes distanceMeter and elevation server-side, and the privacy-to-rulePK mapping (public 1 / private 2). This is exactly the kind of behavioral context annotations cannot carry.

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?

Dense but front-loaded, opening with the endpoint and immediately unpacking the input contract. Every clause carries information; the only cost is that the prose is terse enough to read as a spec note rather than flowing guidance.

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 mutation tool with no output schema, the description covers input shape, defaults, validation, and server-side computation thoroughly. The notable omission is what the call returns (e.g. created course id), which would help an agent chain a follow-up get_course or download_course_gpx.

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 coverage reported at 0%, the description carries the burden and does so well: it lists the CourseInput fields, marks coursePoints/activityTypeId/privacy as optional, gives defaults (1 = running, 'private'), and explains the rulePK mapping the schema does not. It stops short of describing the inner geoPoint fields or the two-point minimum's relation to geoPoints, so not quite a 5.

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 states a concrete action and resource: it POSTs to `/course-service/course` to create a course, and it names the exact `CourseInput` shape. That is clear and specific, but it never distinguishes itself from siblings like create_course_from_gpx or import_course_gpx, which are near-neighbors an agent could confuse it with.

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 no explicit when-to-use or when-not-to-use guidance. Given the presence of create_course_from_gpx and import_course_gpx siblings, the absence of any routing hint for choosing between building a course from raw geoPoints versus importing a GPX is a real gap. Usage is only loosely implied by the required geoPoints.

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