wait_for_action

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful operational context: it blocks until a revision change or timeout, returns the latest state, and waiting can continue after a timeout.

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 compact sentences with the core wait-and-return behavior front-loaded. There is little waste, though the insert-card/anti-calculation clause is slightly context-dependent.

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 wait tool with no output schema, the description covers the trigger, returned value, and post-timeout behavior. It is less complete on timeoutMs semantics, but the schema supplies default and maximum values.

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%: afterRevision is documented in the schema, but timeoutMs has no schema description. The tool description references revision indirectly but gives no semantics for timeoutMs, such as its default or maximum, so it does not compensate for the gap.

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 (wait) and trigger (revision update or timeout), plus the return value (latest state). The clause about insert-card and anti-calculation responses clarifies it is not only for the player's own turn, though it does not name sibling tools directly.

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?

Explains that the tool waits for a revision update or timeout and that it is relevant beyond one's own turn, including when other actions need responses. However, it does not name alternatives such as get_state or clearly specify when not to use it.

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