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

Beyond the annotations' destructiveHint/openWorldHint, the description discloses the concrete destructive effect (prepared or failed result set aside), the side effect (new preparation attempt), the boundary 'This never publishes anything', the cost ('Free'), and the auth requirement ('act' scope). This is meaningfully more than the structured fields provide.

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?

The core effect is front-loaded in the first clause, followed by short, scannable sentences covering the ID requirement, non-publication, cost, and scope. It is dense but largely waste-free; the phrase 'only if this wins' is the one ambiguous bit.

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 destructive mutation with no output schema, the description covers effect, safety boundary, cost, and auth scope, and annotations carry the safety profile. What remains thin is the precondition named awkwardly as 'only if this wins' and the absence of any post-call state or failure expectation.

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 coverage is only 25%, so the description must carry weight. It adds useful semantics for two IDs ('Pass the exact job_id and expected_attempt_id'), implying an optimistic-concurrency guard echoed by the schema's 'exact current managed attempt', but it says nothing about move_id or the optional note, leaving half the parameters unexplained.

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 states a specific verb and resource ('revise an accepted growth move's current managed attempt') and describes the concrete effect: the prepared or failed result is set aside and a new preparation attempt starts. This clearly separates it from siblings like accept_move, adopt_move_result, undo_move, and redraft_output, which imply different outcomes.

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 states the triggering condition ('Apply your user's explicit decision') and the gating constraint ('only if this wins'), giving clear context for when it applies. However, it names no alternative tool for the other branches and never explains when NOT to use it, so it stops short of full routing guidance.

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