Start a paid workflow run

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses that this is a paid operation, that it returns immediately with a receipt and native run_id, that completion must be polled, that idempotency_key re-use is the correct recovery mechanism, and that a fresh key risks double payment. That is exactly the behavioral context annotations cannot carry.

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-loaded with the action and required provenance, then constraints, then recovery. Dense and mostly waste-free, though the closing sentence about technical evidence vs. human creative acceptance is tangential to invocation and could be trimmed.

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 paid mutation tool with no output schema, the description covers the return contract (immediate receipt + run_id), the follow-up polling tool, and the idempotent-retry model. It stops short of stating authentication/permission requirements or failure behavior, which would round it out.

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 0%, so the description must carry parameter meaning; it names five of six params (revision, content_digest, semantic_input_digest, quote_id, idempotency_key) and adds semantics the schema lacks — values must match the quote exactly and the key must be original/preserved on retry. plan_id and the wfp_/wq_/64-hex format expectations are left implicit, keeping it short of a 5.

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 and resource ('Start one explicitly approved paid workflow run') and immediately scopes it against siblings by requiring the quote's exact revision/digests/quote_id. An agent can distinguish this from quote_workflow_plan, approve_workflow_plan, and get_run without opening any schema.

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 explicit preconditions (an already approved run with a quote), explicit prohibitions ('Never auto-approve, auto-quote or invent a new key'), and a recovery path ('If delivery is uncertain, recover with the original request and key; a new key can pay twice'). It also routes the agent to the follow-up sibling ('poll get_run').

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