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

Goes well past the annotations: it discloses that the call spends workspace balance, that it is asynchronous (returns run_id while the run continues), that it is idempotent by request_id with no double charge, and that a needs_confirmation response means nothing started yet. It also flags that row values and outputs are untrusted customer data, a real prompt-injection warning not present in structured fields.

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?

Front-loads the core behavior, then layers cost, confirmation, and polling guidance in a sensible order, with every sentence carrying procedural weight. It is somewhat dense and the test_rows / test_confirm_token passage is tangled, with preview_prompt mentioned separately in a way that slightly overlaps test_rows.

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 15-parameter, nested, asynchronous, cost-incurring tool with no output schema, the description supplies the confirming flow, polling loop, idempotency contract, and the key fields of a needs_confirmation response. Nothing critical an agent needs to invoke it safely is missing.

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?

Adds real meaning beyond the 73%-covered schema: prompt vs prompt_id precedence ('explicit values override the saved prompt'), the list-vs-sheet routing split between output_name and target.sheet.output_column, and the request_id retry semantics. Minor params like temperature, reasoning_effort, verify_output, and overwrite are left entirely to the schema, so it is not fully exhaustive.

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 specific verb, resource, and scope: 'Run an AI prompt once per row of a list or connected sheet.' This is clearly distinguishable from siblings like run_flow, run_scrape, and run_verify, and the per-row fan-out is named up front.

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?

Explicitly routes the agent: call estimate_cost first for pricing, use preview_prompt or test_rows to try a few rows, poll get_run with wait_seconds. It also enumerates the needs_confirmation branch and the confirm_token follow-up, so the agent knows what to do at every decision point.

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