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

With readOnlyHint/not-destructive already declaring the safety profile, the description adds the important behavior: each call blocks up to 55 s and the agent must loop, and latency is driven by queueing and cooldown. It does not disclose what happens on timeout or what the call returns when no state is reached, which matters since there is no output schema.

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 dense sentences, front-loaded with the verb and duration cap, then the calling pattern and rationale. Nothing is redundant.

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?

No output schema exists, so the description should clarify what a call yields (the production's new state? a decision payload?) and how a timeout is signalled. Those gaps remain, though the polling rhythm and duration cap are adequately covered for a read-only wait tool.

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 67%; productionId and untilState are documented in the schema, but timeoutSeconds has only bounds and a default, no description. The description alludes to the state targeting ('reaches a given state') and the 55 s cap that mirrors timeoutSeconds' maximum, but never mentions any parameter by name, so added meaning is minimal.

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?

The description states a specific verb ('Long-polls') and resource ('the production'), plus the terminating conditions ('needs attention, fails or reaches a given state'). It is clear what the tool does but never names the sibling it differs from (get_production), so the blocking-vs-non-blocking distinction is inferred 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?

'Call repeatedly while generation runs' gives explicit operational guidance on the polling loop, and the note about video batches and the shared queue/cooldown explains why repeated calls are expected. It stops short of saying when NOT to use it, e.g. when a simple get_production check suffices.

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