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

With no annotations supplied, the description carries the full behavioral burden and it does disclose the key consequence: an in-progress game ends and is scored on points so far, while a waiting game the caller opened is closed. That is exactly the state-dependent outcome an agent needs before committing. It omits irreversibility, effect on the partner, and permission/error behavior, so a 4 rather than 5.

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 front-loaded sentences with zero filler; the action comes first and the conditional outcome follows immediately. Every clause earns its place.

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, non-annotated mutation-style tool with no output schema, the description covers the important outcome branches but leaves gaps: what happens to the partner, whether the leaver forfeits anything, and what an invalid game_id returns. Adequate but not complete.

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 documented in the schema, game_id is a bare string. The description implies game_id is the game to leave but adds no format, source, or constraint details beyond that inference. Baseline 3 is appropriate.

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?

Specific verb ('Leave') plus a scoped resource ('a word partners game'), which separates it from words_play/words_guess/words_get_game and from dice_leave or tournament_leave that share the verb. It stops short of explicitly naming an alternative, so not a 5.

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 intent to leave a game is implied clearly, and the description splits behavior into two situations (game under way vs. waiting game you opened). There is no explicit when-not guidance, no statement about when to prefer words_get_game or simply abandoning a waiting game, and no mention of invalid-state errors.

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