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

With no annotations provided, the description carries the full burden and does reasonably well: it discloses the permission requirement, that the operation is side-effect free (no time advance, no round completion), that it can be used to reconcile state after reconnection, and that it does not consume the shared daily game-count quota. It stops short of describing the response shape or whether repeated calls are idempotent in cost terms.

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?

Five short, front-loaded sentences with no filler; the permission prerequisite and the read-only nature come first. "Recover acknowledged ticks after reconnecting" is terse to the point of being cryptic, but it is dense information rather than padding.

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 read-only status call with one parameter and no output schema, the description covers permissions, side effects, and quota behavior, which are the important unknowns. However, it neither documents the required sessionId nor characterizes what the returned status contains, so an agent knows why to call it but not precisely what it gets back.

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 0% for the single required sessionId, and the description never mentions it. The phrase "your token's Bathroom session" actually suggests the session is derived from auth rather than passed in, which leaves the caller to work out from the schema alone that a UUID must be supplied. With only one parameter and a trivially typed field, the gap is small but real.

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?

"Read your token's Bathroom session and shared account full-reward availability" gives a specific verb (read) and a specific resource (Bathroom session state plus reward availability), which is far more informative than the bare name. "Does not advance time or complete a round" implicitly separates it from bathroom_game_start/input/finish, but no sibling is named explicitly, so the differentiation is inferential rather than stated.

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?

"Requires play permission" gives a precondition, "Does not advance time or complete a round" gives an explicit negative-use boundary, and "Recover acknowledged ticks after reconnecting" names a concrete use case. What's missing is a direct pointer to alternatives (e.g. use bathroom_game_start to open a session), so the agent must infer routing from the sibling list.

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