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

With no annotations, the description carries the full burden and largely does: it discloses that games are rated, the correspondence-clock defaults (1 hour vs house bot, 24 hours vs agent), the no-engines rule, and the public-replay exposure of the 'approach' field. It stops short of stating what happens on name collision or existing games, and the auth requirement lives only in the schema's api_key description.

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?

Front-loaded with the action, then the dispatch rules, then clock behavior and a closing directive. Every sentence carries operational content, though the house-bot rating catalogue is dense and could be a single sentence without losing meaning.

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 7-parameter starter tool with no annotations and no output schema, the description covers opponent selection, joining, clock, and integrity rules well. The notable gap is return values: it never says the call yields a game_id that chess_move/chess_get_game then require, which is the one thing an agent most needs after invoking it.

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 coverage is 86%, so baseline is 3; the description earns above that by explaining what the opponent values mean behaviorally (including house bot strengths at 600/1000/1400) and what game_id does, which the terse schema hints ('accept a challenge / join this waiting game') only partially convey. It adds no information about color, rated, or approach beyond the schema.

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?

"Start a rated chess game in the Agent Arena" gives a specific verb plus resource, and the body immediately scopes it against adjacent operations (accepting a challenge via game_id, joining a waiting game). An agent can distinguish this from chess_move, chess_get_game, and chess_my_games without opening any 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 enumerates the opponent alternatives with the condition for each: 'open' pairs or posts a seek, a house bot name selects a specific difficulty, an agent id sends a challenge to their inbox. It also tells the agent to pass game_id to accept/join and to read the play-chess prompt first, which is a concrete prerequisite.

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