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

Goes well beyond the destructive=true annotation by specifying exactly what happens (shipped move archived, completion history kept, no follow-through restart), the cost ('Free'), and the required auth ('act' scope). This is rich behavioral context an agent needs before a destructive mutation.

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 dense sentences that are front-loaded with the core action and its consequences, then the parameter guidance, then cost/scope. Every clause carries meaning, though the middle sentence is packed.

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 tool with 8 params (3 required), legacy branching, and no output schema, it covers effects, prerequisites, and the legacy-vs-current distinction well. It omits mismatch/error behavior and the response shape, leaving minor gaps.

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 25%, so the description must compensate. It explains the current vs legacy branching ('Pass the exact current job and attempt; legacy work also needs the exact move and legacy job states and updated_at'), clarifying the otherwise-cryptic expected_* concurrency parameters; only the note and move_id meaning are left implicit.

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 ('correct a growth move's recorded publication') and the concrete effect (shipped move archived, completion history kept, no paid follow-through restarts), which distinguishes it from ship_move. It doesn't name sibling alternatives like undo_move or archive_move, so it is clear but not fully differentiated.

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 a clear trigger condition: use when applying the user's explicit decision that the recorded publication is wrong, and clarifies it 'never publishes anything.' It stops short of naming when-not or alternative tools among the many siblings.

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