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

Adds substantive behavior beyond the annotations: idempotency ('a repeat never starts another worker'), a conditional side effect, cost ('Free'), and an auth scope. With destructiveHint=true already declared, this is meaningful extra context, though reversibility (undo_move) and failure behavior are unstated.

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?

Four short sentences, each earning its place, with the consent gate front-loaded before the mechanical details. No filler.

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, open-world, destructive tool with no output schema, the description covers the core accept flow and idempotency but omits the retry/expected_* path and any outcome description. Annotations cover the safety profile, but the description leaves notable 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 coverage is 71%, so the schema carries most parameter meaning (target enum effects, operation/retry requirements). The description adds no parameter-level detail and instead references 'launch_won', which is not a parameter, leaving expected_legacy_updated_at and retry mechanics entirely to the schema.

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 ('accept a move') and describes the effect: recording a durable preparation attempt and conditionally starting the worker. This distinguishes it from sibling mutators like ship_move/skip_move/undo_move, though it never names them. Clear but without explicit sibling differentiation.

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 real precondition ('only after the founder says yes') and a gating condition for the side effect (launch_won true), plus the 'act' scope requirement. It stops short of naming alternatives such as review_move or ship_move when the founder has not said yes.

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