commit_turn

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

Annotations cover the safety profile (idempotentHint=true, readOnlyHint=false), but the description adds real value beyond them: atomicity, the requirement to reuse exact arguments and key on an unconfirmed retry, and that only a committed receipt proves success. It stops short of describing auth/permission needs or what an uncommitted retry returns.

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, front-loaded sentences with no filler; the commit/atomicity point leads. Slight terseness given the tool's complexity, but every sentence earns its place.

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, 10-required tool with nested objects, 0% schema coverage, and no output schema, this description is far too thin. It omits any guidance on the payload structure, revision/precondition semantics, or what the receipt contains, leaving large gaps an agent cannot fill from structured data.

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% across 15 parameters, so the description carries full burden, yet it only vaguely references 'arguments/key' (likely idempotency_key). It adds essentially no meaning for expected_revision, policy_sha256, preparation_id, outcome, changes, or the other structured fields.

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 (commit) and resource (the authorized scene), and pairing it against the sibling prepare_turn is implicit but inferable. It clearly signals this is the finalization step, though it never names prepare_turn or other siblings explicitly.

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?

Implied usage is present: 'Only a committed receipt means success' tells the agent this is the terminal commit step, and the retry note establishes retry conditions. However, there is no explicit when/when-not or named alternative (e.g. prepare_turn must precede it), so an agent must infer the workflow ordering.

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