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

Adds real context beyond the annotations: the run is asynchronous, models and speech incur usage, approval is required, and the returned identifier must be polled without re-enqueuing while running. That meaningfully supplements the destructive/openWorld/non-idempotent hints, though it doesn't say what happens to an in-flight run if the call is repeated.

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 short sentences, front-loaded with the action and then the cost/approval/polling constraints. Nothing is redundant and every sentence carries an operational fact.

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?

Covers the async lifecycle and cost/approval model, which is what an agent needs to invoke a 3-parameter paid job. It does not name the polling tool or clarify the relationship to the batch-start sibling, which keeps it short of a 5.

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%, with confirm and id already documented in the schema, so the baseline is 3. The description reinforces the approval semantics of confirm but adds no new syntax or format detail for the nested data options.

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 clear verb and object: 'Queue an asynchronous test', which tells an agent this starts an async execution rather than creating a definition. It never names the 'simulation run' or distinguishes itself from siblings like start_simulation_batch, so 4 rather than 5.

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?

Gives procedural guidance ('Approve the run first', 'poll the returned identifier', 'do not enqueue again while it is running') but does not say when to choose this over start_simulation_batch or create_simulation. Usage is implied by context, not by explicit alternatives.

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