Skip to main content
Glama

Start or Recover Match Ranked Run

horizon_start_match_ranked_run
Idempotent

Creates or recovers one original match-bound validated run after complete consensus. Use when: explicit asynchronous multiplayer actions after reading horizon://docs/matches.

Instructions

Creates or recovers one original match-bound validated run after complete consensus. Use when: explicit asynchronous multiplayer actions after reading horizon://docs/matches. Not for: automatic polling, page traversal, timeout progression, invented winners or automatic rewards. Reconcile with horizon_get_matches and horizon_get_match. Consent and game consensus do not validate honest gameplay. Requires: userId and the player's session: sign in with horizon_signin_email or horizon_signin_anonymous and pass its accessToken as sessionToken. Side effects: One HTTP attempt. Server rechecks the original configured board and binds match/final revision. Recovery preserves runId, seed and expiry; never replaces consumed/expired tickets. This short post-match validation is not retrospective game simulation. Returns: Existing StartRunResponse with original ticket, runId, seed, expiry and context status; submit through the existing validated-actions endpoint. Errors: 404 hides private/missing/expired matches. 409 REVISION_CONFLICT or STATE_CONFLICT: explicitly reread and reconcile the original intent, never replace the revision or automatically resubmit. RESULT_CONFLICT preserves the original report. RUN_EXPIRED/RUN_ALREADY_USED never allow replacement ranked runs. 422 ACCOUNT_MATCH_LIMIT_REACHED refuses create only, when the account's open matches (lobby, running, reporting) across all its projects are at the plan limit; join, turns, leave, report and cancel are not blocked, so wait for matches to finish instead of retrying. 501 FEATURE_NOT_SUPPORTED is explicit for simpleServer ranked mode. 401 means the session is missing or expired: sign in again and retry with the new accessToken. 403 for a session means the token belongs to another user: pass the userId that signed in. Needs HORIZON_API_KEY. Every failure returns an error result (isError) with the HTTP status and body: a 401 that horizon_test_connection also returns means HORIZON_API_KEY is wrong, 429 means the account's per-minute rate limit was reached (wait a minute, then retry).

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": {
      "userId": "<userId>",
      "sessionToken": "<sessionToken>",
      "matchId": "<matchId>",
      "finalStateRevision": "<finalStateRevision>"
    },
    "name": "horizon_start_match_ranked_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
userIdYesActive player matching the session and project
matchIdYesOriginal server match UUID in the selected project
sessionTokenYesPlayer accessToken sent only as Bearer
finalStateRevisionYesOriginal reviewed revision; never substitute a newer revision after an uncertain write

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.1

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnly=false, idempotent=true, openWorld=true, destructive=false. The description adds far more: a single HTTP attempt, server re-verification of the original configured board, binding of match and final revision, and exactly what recovery preserves (runId, seed, expiry) versus what it never replaces (consumed/expired tickets). Failure semantics are enumerated per status code (404, 409, 422, 501, 401, 403, 429), which is behavior an agent cannot get 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.

Conciseness4/5

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

Front-loads purpose and then uses labeled sections (Use when, Not for, Requires, Side effects, Returns, Errors) that make it scannable. The error catalog is long and repeats some points (revision replacement, no resubmission) but each entry maps to a distinct agent decision, so little is pure filler.

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?

For an open-world mutation with no output schema, the description still covers authentication prerequisites, side effects, the exact return payload (ticket, runId, seed, expiry, context status) and the follow-up endpoint. Error handling and recovery rules are complete enough that an agent can call it and react correctly without further context.

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?

Schema description coverage is 100%, so all four parameters are already documented, including finalStateRevision's 'never substitute a newer revision' rule. The description only adds the operational link that sessionToken is the accessToken from horizon_signin_email or horizon_signin_anonymous, which the schema already hints at ('Player accessToken sent only as Bearer'). Baseline 3 is appropriate.

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

Purpose4/5

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

States a specific verb and resource: 'Creates or recovers one original match-bound validated run after complete consensus.' The qualifiers 'match-bound', 'original' and 'recover' separate it from a plain run-start tool. It never names the closest sibling (horizon_start_run) explicitly, so the differentiation is inferential rather than stated.

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 an explicit 'Use when' condition (asynchronous multiplayer actions after reading horizon://docs/matches), a 'Not for' exclusion list (polling, page traversal, timeout progression, invented winners, automatic rewards), and names the tools to reconcile with: horizon_get_matches and horizon_get_match. It also warns that consent/consensus does not imply honest gameplay.

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

Deploy Server

Other Tools