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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds real behavioral context with the name-resolution fallback chain (GPX `<name>`, then filename), which is beyond the annotations, but says nothing about failure modes or what happens if the GPX has no name and no usable filename.

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?

Two short sentences, front-loaded with the composite identity and followed by the only non-obvious default. No filler, nothing redundant with the schema.

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 no return description, an agent calling this mutation tool cannot tell whether it returns the new course, an id, or nothing, nor what partial-failure looks like if the import succeeds but the create fails. The name-default rule is covered, but the post-call picture is incomplete.

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 75%, and the description supplies the missing piece: the defaulting behavior of the `options.name` parameter, which the schema leaves entirely undocumented. This adds genuine meaning beyond the structured fields, even though filename/encoding semantics come from the schema.

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 the tool is `importCourseGpx` then `createCourse` in one call, which precisely defines the operation as creating a course from a GPX source. It distinguishes itself from the `create_course` and `import_course_gpx` siblings by being the composite shortcut, though it never spells out the resource noun 'course from GPX' in plain terms.

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?

By framing itself as two existing calls combined, it implies you should use this instead of invoking `import_course_gpx` and `create_course` separately, but it never states that explicitly or names when to prefer the individual siblings. Usage is inferable rather than stated.

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