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

Annotations only indicate non-read-only and non-destructive. The description adds meaningful behavioral context beyond annotations: the operation is durable, one preparation attempt is recorded, a worker may start only under a specific condition, repeats are idempotent with respect to worker launch, and there is a scope requirement. This is strong transparency for an action with side effects.

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 with high signal density. The key operational constraint is front-loaded, followed by behavioral consequences and cost/scope info. No filler or repetition of schema details.

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 7-parameter tool with retry/legacy-state complexity and no output schema, the description covers only the happy-path semantics. It does not describe the operation parameter, retry requirements, legacy state usage, or what a caller should expect in response. An agent navigating this tool would lack critical context for valid invocation across all supported cases.

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 only 43%, which is below the 50% threshold, so the description needed to compensate for undocumented parameters. It does not explain move_id, target, operation, expected_attempt_id, or the legacy fields. The retry and expected-state parameters remain opaque to an agent trying to construct a valid call.

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 clearly states the action ('accept a move'), the precondition ('only after the founder says yes'), and the core effect (records a durable preparation attempt, may start a worker if launch_won is true). However, it does not explicitly distinguish itself from sibling tools like review_move, ship_move, or skip_move, so differentiation is mostly implicit.

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?

It provides concrete usage guidance: only accept after founder approval, worker launch is conditional on launch_won, repeats never start another worker, and the 'act' scope is required. It does not explicitly contrast with sibling tools or explain when to use the retry operation, which leaves some routing to inference.

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