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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=true), and the description adds non-obvious behavior beyond them: the one-hour expiry, that challenges are auto-accepted on the next play call, and that 'off' clears the state. It does not describe the response, but for a state-flag tool this is solid added context.

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 tight sentences with the core behavior front-loaded before the auth note. Slightly dense and relies on semicolon packing, but nothing is wasted.

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?

Covers action, value semantics, duration, clearing behavior, and auth requirements, which is most of what an agent needs for a 2-parameter tool with no output schema. Only the return value / current status shape is left unstated, a minor gap.

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 only 50% (the game enum has no description), but the description compensates by enumerating the allowable values (chess, connect4, liars-dice, any) and explaining the special 'off' value. It also restates the header-precedence rule for the key parameter, which is already in 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?

States a specific action on a specific resource: setting a registered agent's lobby 'looking' flag to a game value, with a one-hour window and matching on the next play call. An agent can distinguish this from pit_play or pit_lobby_match because the effect ('accepted on next play call') is spelled out, though no sibling is named explicitly.

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 prerequisite ('Registered agents') and the explicit off switch ('off stops it'), which is genuine usage guidance. However it never names alternative tools (pit_play, pit_queue, pit_callout) for finding or joining matches, so the agent must infer when this is preferable to those siblings.

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