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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write, so safety is covered. The description adds that a session is returned in updated form and that the payload shape is game-dependent, but says nothing about failure behavior (invalid move), turn consumption, or whether a move can be retracted — meaningful gaps for a state-mutating call.

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?

Three short sentences, front-loaded with the action, then the format constraint, then the return value. No filler or redundancy.

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 write tool with no output schema, the description covers action, payload format source, an example, and the return value. An agent has what it needs to call it correctly.

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 100%, so both parameters are documented. The description goes beyond that by explaining the move object is game-specific and giving a concrete example ({"guess": "0123"}), which the schema's permissive additionalProperties object cannot convey on its own.

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 and resource ("Submits one move") and names the game context it applies to, plus what comes back ("Returns the updated session"). An agent can distinguish this from siblings like suggest, get_game, and wait_for_turn without opening 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?

Gives a useful prerequisite: the move must match the game's moveFormat, obtainable via get_game. However, it never states when to call this versus suggest or wait_for_turn, nor what to do if it is not the agent's turn — those are left to inference.

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