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

With annotations only covering readOnlyHint=false and destructiveHint=false, the description adds real behavioral context: the job is asynchronous, it is metered ('Billed per replayed record (REPLAY metric)'), and it is role-gated. It still omits cost magnitude, concurrency limits, and whether the job can be cancelled (lexq_replay_cancel exists as a sibling).

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 with the purpose and measurement outcome front-loaded, followed by the operational constraints. No filler, and the routing hint lands last where it is most actionable.

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 4-param async job tool with no output schema, the description covers what the job does, that it is async, that it costs money, and how to poll. It does not say where results land or what the job payload looks like on completion, though lexq_replay_status and lexq_replay_export cover that.

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 description coverage is 100%, so from/to timezone semantics, the maxRecords cap, and candidateVersionId are already fully documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 gives a precise verb and resource ('Submit an async job that replays a date window of past executions against a candidate version') plus the defining output ('measures the blast radius (how many decisions change)'). That outcome framing clearly separates it from the simulation/dry-run siblings without needing to enumerate them.

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?

It states the follow-up workflow explicitly ('Poll with lexq_replay_status') and a hard precondition ('VIEWER role cannot submit'), which tells the agent both how to proceed and who may call it. It stops short of naming the nearest alternatives (lexq_simulation_start, lexq_dry_run) or when blast-radius replay is preferred over them.

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