Skip to main content
Glama

Race prediction

get_race_prediction
Read-onlyIdempotent

Predict an athlete's finish times for 5K, 10K, half marathon and marathon from their best recent race result, using VDOT (a running-fitness index derived from race performances). Returns the VDOT, the reference race it came from and one prediction per distance with a confidence: high when the VDOT and Riegel estimates agree within 5%, otherwise medium. Only road-running results at 5K to marathon count; without one the call fails with no prediction. A coach sees it only when the athlete shares training and pace data.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "athlete_id": "<athlete_id>"
    },
    "name": "get_race_prediction"
  }
}

Input Schema

NameRequiredDescriptionDefault
athlete_idYesThe athlete's user id: get_current_user's athlete_id for the connected account, or an id from get_coach_athletes or find_athlete.

Output Schema

NameRequiredDescriptionDefault
vdotNoVDOT: a running-fitness index from race results (higher is fitter).
errorNo
statusNo
messageNo
privacyNoPresent when the athlete's settings withhold data.
warningsNo
next_stepNoWhat can be done next, for example after a failure.
athlete_idNo
next_cursorNoReads the next page; null on the last page.
predictionsNo
reason_codeNo
total_weeksNo
user_contentNoFields in this result that people wrote.
reference_raceNo
weeks_returnedNo
truncated_fieldsNoLists cut to fit one response: rows returned and total.
generated_contentNoFields in this result that NexRex's AI wrote.
session_definitionsNoSessions that several rows of this result share by session_ref.
content_block_fieldsNoColumn names of every content_blocks row, nested blocks rows included.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / content_block_fields / description
      Previous value: -"Column names of every content_blocks row."New value: +"Column names of every content_blocks row, nested blocks rows included."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description still adds genuine behavior: the exact return shape (VDOT, source race, one prediction per distance), the confidence rule (high when VDOT and Riegel agree within 5%, else medium), and the hard failure mode when no qualifying race exists. Auth gating is also disclosed - a coach only sees it when the athlete shares training and pace data - which is context an agent cannot derive from the annotations.

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

Conciseness5/5

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

Four sentences, front-loaded with the purpose, then return shape, then the eligibility constraint and failure mode, then the access rule. Every sentence contributes distinct information with no restatement of the name or annotations.

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

Completeness4/5

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

Covers method, return values, confidence semantics, failure conditions and permission gating for a single-parameter read tool; an agent could call it correctly from this text alone. An output schema exists, so the description carries no obligation to detail the payload, leaving only minor room for richer failure detail (e.g. what error surface appears).

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

Parameters3/5

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

Only one parameter and the schema documents it at 100% coverage, including how to obtain the id from get_current_user, get_coach_athletes or find_athlete. The description adds no additional meaning about athlete_id, so the baseline 3 applies.

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 (predict), the exact resource (finish times for 5K, 10K, half marathon, marathon) and the method (VDOT derived from race performances). No other sibling produces predictions, so it is trivially distinguishable from get_race_info or get_activities.

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

Usage Guidelines4/5

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

Gives a clear precondition (the athlete must have a road-running result between 5K and marathon) and a clear when-not (without one the call fails with no prediction). It does not name an alternative tool for the no-result case, which would have pushed this to a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources