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

The description adds substantial behavioral context beyond the annotations: it runs synchronously, preserves existing CRSProf, returns warnings and a structured summary, does not invent pace/time without timestamps, and does not create a session-specific browser link. It also discloses a subtle measurement caveat about detected stop elapsed. These are exactly the non-obvious behaviors an agent needs.

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 long but dense and front-loaded with the core purpose. Each sentence adds a distinct piece of information: output shape, defaults, caveats, hosted-client workaround, and execution model. Slight trimming could improve it, but nothing is redundant enough to penalize heavily.

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 tool with this complexity—three nested parameter groups, no required parameters, and an output schema—the description covers the important gaps: what sources are accepted, key defaults and guards, edge-case behavior around timestamps and stop detection, the hosted-client upload workflow, and the synchronous execution model. The agent has enough to call and interpret the tool correctly.

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 only 33% at the top level, but the description compensates by explaining accepted sources (inline course_file, URL, or artifact), defaults for moving threshold, minimum stop, and merge distance, and important algorithm selection context. It does not describe every option field in detail, but the schema already documents the nested properties reasonably well.

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 opens with a specific verb and resource: 'Analyze supplied GPX/FIT directly with the browser's canonical pipeline.' It clarifies that this is not a catalog search or runner-profile build, distinguishing it from the sibling tools import_course and generate_runner_profile.

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 gives clear context for when to use the tool: direct analysis of a supplied GPX/FIT file with no catalog or runner profile needed. It also gives an explicit when-not: hosted clients without file-byte access or direct upload connectivity should use the fixed upload page instead of this MCP call. It does not explicitly name sibling alternatives, but the routing guidance is strong.

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