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

With no annotations, the description carries the full burden and does so: unrated/no-rating-impact, two-game set with sides swapped, one-game mode on the pool, rate limits (5/min, 60/day), 7-day retention, returns match_id requiring get_match polling, and which inputs are rejected. That is unusually rich behavioral disclosure for a mutation-style tool.

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?

Nearly every clause carries information, but it arrives as an unstructured run-on with a typo and a mid-sentence topic shift into "Bench practice", so the reader must re-parse to separate general behavior from pool mode. Front-loading the unrated/no-rating guarantee is a plus.

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 10-parameter, annotation-free tool with no output schema, the description covers the outcome (match_id), the follow-up procedure, and the constraints. Remaining gaps are the semantics of key, version, and theater, which an agent must infer from the schema alone.

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?

It adds real meaning beyond the 70%-covered schema: what vs accepts, that pool must be "bench-public" with index 0..15, that side/games control one-vs-two game behavior, and that the Bench member plays at a pinned version on Armor rules. It leaves key, version ("by label"), and the armor/sub theater enum largely unexplained.

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?

"Test one of your bots on a map seed you choose against any bot... without touching any rating" states a specific verb plus resource and distinguishes it from the rated ladder siblings. The core intent is unmistakable, though the run-on sentence and the garbled phrase "your bot is always a in the result" slightly blur the edges.

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?

It gives clear conditions for use (pick a seed, play a house style or Bench panel member, practice on the bench-public pool) and names the alternative flow via get_match polling. It also states two exclusions: benchmark seeds are refused and R6–R9 are private. What's missing is a direct "use X instead for rated games" routing to enrol_ladder.

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