Start or Recover Match Ranked Run

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

Goes far beyond the annotations (idempotent, openWorld, non-destructive) by disclosing that a single HTTP attempt is made, that the server rechecks the original board and binds match/final revision, that recovery preserves runId/seed/expiry and never replaces consumed tickets, and by enumerating auth requirements (HORIZON_API_KEY, sessionToken via signin) and error semantics (404 concealment, 409 conflicts, 401/403 handling, 429). This is unusually rich behavioral context.

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?

Structured into labeled sections (Use when / Not for / Requires / Side effects / Returns / Errors) that are front-loaded and scannable. It is long and dense, with some redundancy across the requirement and error prose, but nearly every sentence carries operational value and the important scoping constraint leads.

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 complex, stateful mutation with recovery semantics, the description covers prerequisites, side effects, return shape, and the full error taxonomy, and no output schema exists so this prose appropriately carries the return-value burden. An agent has everything needed to invoke it correctly and handle failures.

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 100%, so the baseline is 3. The description adds genuine value beyond the schema: it explains the sessionToken sourcing workflow (sign in and pass the accessToken as sessionToken), states userId must be the signing-in player on 403, and reinforces that finalStateRevision must never be substituted with a newer revision after an uncertain write.

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?

States a specific verb (creates or recovers) and a precisely scoped resource (one original match-bound validated run after complete consensus), which clearly distinguishes it from horizon_start_run and horizon_report_match_result. An agent can tell it apart from siblings without reading the schema.

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?

Explicitly names the 'Use when' condition (explicit async multiplayer actions after reading match docs) and the 'Not for' exclusions (automatic polling, page traversal, timeout progression, invented winners, automatic rewards), plus names horizon_get_matches and horizon_get_match as reconciliation partners. When-to-use, when-not, and alternatives are all present.

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