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

With readOnlyHint=true already in annotations, the description adds substantial runtime semantics: RUNNING reports progress 0–100, COMPLETED fills summary and changedSamples, FAILED carries errorMessage, and capped=true explains partial replay. These details give an agent a complete contract for interpreting the returned state without needing an 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?

Three sentences deliver the core action, the status mapping, and the capped special case. Every sentence carries functional information; the task is clear in the first sentence and the remaining clauses are dense but essential.

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?

Since there is no output schema, the description must and does explain what state values mean and what fields appear in the COMPLETED and FAILED cases. The capped flag is also clarified. With a single required parameter and all runtime states disclosed, nothing an agent needs to call and interpret this tool correctly is omitted.

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?

The only parameter jobId already has a 100% descriptive schema reference ('Replay job ID from lexq_replay_start'), so the description adds little beyond reiterating that the tool polls a window replay job. With high schema coverage, baseline 3 applies and no compensation is required.

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 opens with a specific verb and resource ('Poll a window replay job') and names the outcome states. This clearly distinguishes the tool from action-based replay siblings like lexq_replay_start, lexq_replay_cancel, and lexq_replay_export, as well as from the parallel lexq_simulation_status.

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?

The phrase 'Poll a window replay job' establishes the intended context: the agent is checking the progress or completion of an earlier replay job. It does not explicitly point to lexq_replay_start as the source of jobId or warn against using it for other purposes, but the role of a status poller is unambiguous and the naming matches the sibling set.

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