import_course_gpx

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

Goes far beyond the annotations (readOnly=false, openWorld=true, destructive=false) by disclosing exact side-effect behavior: nothing is saved, courseId is null, the track is resampled (13 points become 37), elevations/timestamps are null, courseName comes from the GPX <name>, and a GarminError is thrown on an empty response. This is rich behavioral context the annotations do not 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: endpoint first, then the critical parse-only behavior bolded, then edge behaviors. Every clause carries signal, though the run-on semicolon structure is heavier than ideal.

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 compensates fully by describing the return shape (courseId null, resampled track, null elevations/timestamps, courseName) and the empty-response error. Combined with the annotations covering safety/open-world, an agent has everything needed to call and interpret this tool.

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 coverage is 100% and the single filePath param is documented in the schema, so the baseline is 3; however the description adds meaningful value by restricting accepted input to '.gpx only' (explicitly noting only .gpx was verified) even though the schema lists .fit/.gpx/.tcx, plus the transport field name 'file'. This narrows and corrects the schema semantics.

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 specific action (multipart POST that parses a GPX course), names the endpoint, and front-loads the crucial 'saves NOTHING' semantics that separate it from persistence tools like create_course_from_gpx. An agent can immediately tell this is a parse-only operation rather than a create/import that persists.

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 clearly establishes the usage context (parse-only, no save, .gpx only) so the agent knows when this applies versus a saving variant, but it never names an explicit alternative or states 'use X to persist'. Context is clear but exclusions/routing to siblings are left implicit.

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