flow.record_test_run

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

There are no structured annotations, so the description carries the transparency burden. It explicitly declares '[workspace write][risk:write]', which tells the agent this is a mutating operation with risk, and it discloses the key side effect: the latest passed run becomes the default replay path. It stops short of describing overwrite/append behavior or idempotence, but the most important behavioral traits are present.

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?

The description is a single compact sentence with risk tags front-loaded and no filler. Every part contributes either to identifying the operation or to explaining its consequence.

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 write tool with no annotations, no output schema, and seven undocumented parameters, the description gives a good high-level picture but is not fully complete. An agent would benefit from more detail about required status values, optional fields like runId, and how this compares with the related flow.record_checkpoint/replay tools.

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?

With 0% schema description coverage, the description must compensate. It adds meaning by clarifying that checkpointIds are ordered and that a 'passed' status makes the run become the default replay path. However, it leaves runId, artifacts, startedAt, finishedAt, and the exact status vocabulary to be inferred from parameter names alone.

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 uses a specific verb ('Record') and a precise resource ('ordered checkpoint ids for a test run'), and it explains the downstream purpose ('The latest passed run becomes the default replay path'). This makes it distinguishable from sibling tools like flow.record_checkpoint, which is about a single checkpoint rather than a whole test run.

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 description implies it is used when persisting a test run's checkpoint sequence, especially to influence later replay. However, it does not explicitly state when to prefer this over flow.record_checkpoint, flow.plan_replay, or flow.replay_to_checkpoint, nor does it mention any alternative conditions.

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