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

Despite having annotations (readOnlyHint false, openWorldHint true, etc.), the description adds substantial behavioral context: it preserves and summarizes existing CRSProf, returns a bounded structured summary with units and missing-data warnings, explains stop detection caveats, and clarifies that missing timestamps do not produce invented pace/time. It also discloses synchronous execution and the fallback flow, going well beyond what annotations provide.

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 dense but well-organized: core purpose is front-loaded, then defaults, caveats, fallback, and execution details follow. Each sentence contributes critical operational information, so the length is justified even if it could be trimmed slightly.

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?

Given the tool's complexity (three nested object parameters, no required fields, multiple source kinds) and the presence of an output schema, the description covers all necessary aspects: input formats, defaults, return contents, error handling, synchronous behavior, and a precise fallback for hosted clients. An agent can confidently select and invoke this tool from the description alone.

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?

The schema covers only 33% of parameters with descriptions, but the description compensates by explaining defaults (moving threshold 0.25 m/s, minimum stop 30 s, merge distance 60 m) and contextualizing the source and course_file parameters (e.g., inline content vs. artifact ID, fallback for hosted clients). This adds meaning beyond the bare schema, though it does not detail every option nuance.

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–resource pairing: 'Analyze supplied GPX/FIT directly with the browser's canonical pipeline,' and immediately distinguishes it from catalog search or runner profile generation. This separates it from siblings like search_race_catalog and generate_runner_profile without ambiguity.

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 clearly states when to use the tool (direct analysis of GPX/FIT) and when to avoid it (hosted clients without file access, which should direct users to the fixed upload page). It also notes synchronous execution and job inspection. However, it does not explicitly name alternative tools or outline exhaustive when-not-to-use conditions, so it is strong but not fully explicit.

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