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

With no annotations provided, the description carries the full burden and delivers: it discloses server-side archive expansion, skipped nested archives and duplicates, per-file parse failure reporting, rejection of local paths/file:// URLs, and necessity of user-approved evidence selection. It also clarifies that USRProf goes beyond average pace and that evidence choice affects downstream race-plan times. No annotation contradiction exists.

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 lengthy but front-loaded: purpose in the first sentence, then use-when guidance, then evidence details, then the Strava sibling, then next step. Some redundancy exists between the main description and the sources parameter description (both warn against blindly including files), but every sentence earns its place given tool complexity.

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 3 parameters, 33% schema coverage, nested objects, and an output schema, the description covers the full workflow: prerequisites, evidence acceptance, archive behavior, intent selection, sibling routing, and the postcondition of passing the artifact ID to create_race_plan. Nothing essential is missing for correct invocation.

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%, so the description must compensate. It does: sources are tied to POST /api/artifact-uploads purpose runner_evidence vs usrprof_source, archives vs raw_file/url are distinguished, and profile_intent is linked to asking the user and selecting evidence accordingly. The description even calls out that only segment_evidence model is supported, adding meaning absent 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 opens with a clear verb-resource pair: 'Generate a segment-evidence USRProf runner profile artifact from uploaded runner evidence or an existing .usrprof source.' It distinguishes itself from siblings by explicitly directing Strava use to build_runner_profile_from_strava and by naming create_race_plan as the downstream consumer. The purpose is unambiguous and not a tautology.

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 explicitly states when to use the tool ('Use this when the user does not already have an already-converted usrprof_artifact_id'), instructs to ask the user for profile intent first, and gives a hard exclusion: 'For Strava, do not use generate_runner_profile and never ask for credentials or tokens. Call build_runner_profile_from_strava.' It also provides evidence-selection safeguards, such as summarizing candidates and getting user approval.

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