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

With no annotations, the description carries the full burden and does a good job disclosing consequences: forfeiting an in-progress game, closing a self-opened waiting table, or releasing a seat at someone else's table. It stops short of saying whether the forfeit counts as a recorded loss or whether the player can rejoin afterward.

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?

Two crisp sentences, front-loaded with the action, followed by the conditional outcomes. Every clause carries information and nothing is padded.

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 two-parameter, no-output-schema action tool, the description covers the important part: what leaving does in each game state. The remaining gap is practical guidance on sourcing game_id and confirming what a successful leave returns.

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 50%: api_key is well documented in the schema itself, but game_id has no description anywhere. The description does not explain how to obtain game_id (e.g., via dice_my_games or dice_get_game), so it adds no meaning beyond the self-evident field name.

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?

The description opens with a specific verb and resource ('Leave a liar's dice game'), immediately distinguishing it from siblings like dice_play, dice_bid, and dice_get_game. It wastes no words on tautology and the scope of the action is unambiguous.

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?

The state-dependent outcomes imply when the tool applies (you are in a game or seated at a table), but there is no explicit when-to-use guidance, no mention of tournament_leave as a related alternative, and no note on prerequisites such as needing to actually be seated.

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