CourseProfiler

Generate runner profile

generate_runner_profile

Generate a segment-evidence USRProf runner profile artifact from uploaded runner evidence or an existing .usrprof source. Confirm profile purpose and evidence selection only if not already explicit. Do not silently use every local file. profile_intent is advisory: the server does not filter sources. Evidence supports pacing, durability, terrain fit, uphill running limits, and confidence; get_runner_profile_requirements explains selection. Accepted evidence includes GPX/FIT/CRSProf activity files, ZIP/TAR/TAR.GZ/TGZ/TAR.XZ/TXZ archives containing those files, and .usrprof files passed as source_file artifacts from POST /api/artifact-uploads, raw_file inline content/base64, or fetchable HTTPS URLs. Archives must use purpose runner_evidence, are expanded server-side, and report skipped nested archives, duplicate contents, unsupported entries, and parse failures by filename/path. For Strava, call build_runner_profile_from_strava and never ask for credentials or tokens. Follow its browser-consent/job flow. Pass the generated usrprof artifact ID to create_race_plan as runner.usrprof_artifact_id.

Input Schema

Name	Required	Description
`sources`	Yes	Runner evidence/profile sources. Use uploaded source_file artifact IDs from POST /api/artifact-uploads with purpose runner_evidence for GPX/FIT/CRSProf activities or ZIP/TAR/TAR.GZ/TGZ/TAR.XZ/TXZ archives containing evidence files; use usrprof_source for .usrprof. Archives are expanded server-side, nested archives are skipped with warnings, exact duplicate contents are skipped, and unsupported/corrupt entries are reported per filename/path. Or use raw_file/url when the MCP client can proxy bytes. Local paths and file:// URLs are not accepted. Choose evidence according to profile_intent; do not blindly include all available files without user approval.
`import_options`	No
`profile_intent`	No	profile_intent is advisory context for the agent. The server does not filter or select evidence from it; submit only user-approved sources.

Output Schema

Name	Required	Description
`errors`	No
`job_id`	Yes	CourseProfiler job ID to poll with get_job.
`status`	Yes	Job status, e.g. queued, running, succeeded, or failed.
`progress`	No
`warnings`	No
`created_at`	No	ISO-8601 creation timestamp.
`expires_at`	No	ISO-8601 expiration timestamp.
`started_at`	No	ISO-8601 start timestamp, when available.
`status_url`	No	Relative API URL for polling this job.
`completed_at`	No	ISO-8601 completion timestamp, when available.
`result_artifacts`	No	Artifacts produced by the job, including role metadata.
`submission_request_id`	No	Request ID that originally allocated this job; absent in legacy metadata.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 14, 2026

addedOutput schema / properties / submission_request_id

Added value: +{
+  "description": "Request ID that originally allocated this job; absent in legacy metadata.",
+  "type": "string"
+}

Changed1 schema field changedSep 22, 2026

changedOutput schema / properties / result_artifacts / items / properties / download_url / description

Previous value: -"Private short-lived download URL. Share only with the user."New value: +"Artifact download URLs are private and short-lived; share them only with the user, verbatim in a code block, not a clickable link. Ask the user to copy the entire URL into their browser address bar. Do not rewrite the URL or add tracking parameters such as utm_source: changes invalidate the signature. If expired, call get_artifact for a fresh URL. This applies only to artifact download_url values, not authorization or upload links."

Changed1 schema field changedSep 7, 2026

addedInput schema / properties / profile_intent / description

Added value: +"profile_intent is advisory context for the agent. The server does not filter or select evidence from it; submit only user-approved sources."

Changed1 schema field changedJul 15, 2026

changedInput schema / properties / sources / description

Previous value: -"Runner evidence/profile sources. Use uploaded source_file artifact IDs from POST /api/artifact-uploads with purpose runner_evidence for GPX/FIT/CRSProf activities or usrprof_source for .usrprof, or use raw_file/url when the MCP client can proxy bytes. Local paths and file:// URLs are not accepted. Choose evidence according to profile_intent; do not blindly include all available files without user approval."New value: +"Runner evidence/profile sources. Use uploaded source_file artifact IDs from POST /api/artifact-uploads with purpose runner_evidence for GPX/FIT/CRSProf activities or ZIP/TAR/TAR.GZ/TGZ/TAR.XZ/TXZ archives containing evidence files; use usrprof_source for .usrprof. Archives are expanded server-side, nested archives are skipped with warnings, exact duplicate contents are skipped, and unsupported/corrupt entries are reported per filename/path. Or use raw_file/url when the MCP client can proxy bytes. Local paths and file:// URLs are not accepted. Choose evidence according to profile_intent; do not blindly include all available files without user approval."

Changed2 schema fields changedJul 14, 2026

addedInput schema / properties / profile_intent

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "selection_notes": {
+      "description": "Evidence selection strategy approved by the user, e.g. recent mountain races only; exclude road 10Ks.",
+      "type": "string"
+    },
+    "target_distance_km": {
+      "description": "Approximate target distance in km, used by assistants to choose similar evidence.",
+      "type": "number"
+    },
+    "target_elevation_gain_m": {
+      "description": "Approximate target elevation gain in meters, used by assistants to choose similar evidence.",
+      "type": "number"
+    },
+    "target_race_name": {
+      "description": "Target race/course name when building a race-specific profile.",
+      "type": "string"
+    },
+    "terrain": {
+      "description": "Terrain/technicality notes, e.g. technical mountain trail, runnable gravel, high altitude.",
+      "type": "string"
+    },
+    "type": {
+      "description": "Why this profile is being built. Ask the user before choosing evidence.",
+      "enum": [
+        "target_race",
+        "target_distance",
+        "general_trail",
+        "insights_only"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [],
+  "type": "object"
+}

changedInput schema / properties / sources / description

Previous value: -"Runner evidence/profile sources. Use uploaded source_file artifact IDs from POST /api/artifact-uploads with purpose runner_evidence for GPX/FIT/CRSProf activities or usrprof_source for .usrprof, or use raw_file/url when the MCP client can proxy bytes. Local paths and file:// URLs are not accepted."New value: +"Runner evidence/profile sources. Use uploaded source_file artifact IDs from POST /api/artifact-uploads with purpose runner_evidence for GPX/FIT/CRSProf activities or usrprof_source for .usrprof, or use raw_file/url when the MCP client can proxy bytes. Local paths and file:// URLs are not accepted. Choose evidence according to profile_intent; do not blindly include all available files without user approval."

AddedJul 14, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare write semantics (readOnlyHint=false, idempotentHint=false, openWorldHint=true), so the bar is lower, yet the description still adds real behavior: server-side archive expansion, skipped nested archives, duplicate-content skipping, per-filename reporting of unsupported/corrupt entries, rejection of local/file:// paths, and the runner_evidence/usrprof_source purpose requirement. It stops short of stating whether re-running creates a new artifact or how long generation takes, keeping it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then routing rules, then a dense but useful enumeration of accepted formats and source kinds. The evidence-format sentence is long and reads as a wall of extensions that could have been compressed, but every remaining sentence carries actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the description covers the gaps that matter for this complex, nested 3-parameter write tool: input provenance, archive behavior, credential avoidance, advisory-status of profile_intent, and downstream handoff. An agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the description compensates: it clarifies that profile_intent is advisory only and the server does not filter sources, that archives must carry the runner_evidence purpose, and which source kinds map to which upload purposes. It adds genuine semantics beyond the schema, though it doesn't revisit every nested property.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (generate) and resource (segment-evidence USRProf runner profile artifact) plus the two accepted input families (uploaded runner evidence or an existing .usrprof source). It clearly differentiates from the sibling build_runner_profile_from_strava and from create_race_plan by naming both explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit routing rules: use build_runner_profile_from_strava for Strava and never ask for credentials, consult get_runner_profile_requirements for selection, and hand the resulting usrprof artifact ID to create_race_plan as runner.usrprof_artifact_id. It also warns against silently using every local file and against synthesizing evidence.

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

All CourseProfiler tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?