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

The description adds meaningful behavior beyond the sparse annotations: it discloses the 'act' scope requirement and explains the real-world consequence of late or inaccurate reporting ('AfterLaunch measures what a move earns only once it knows it is live'). It also stresses truthfulness. No contradiction with annotations.

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 description is compact and front-loaded with the core action, then the WHEN guidance. It is slightly repetitive ('Report only what is true' is re-emphasized by the drafted/staged/awaiting-review exclusion), but the extra context earns its place for an agent that must self-report progress.

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 state-reporting tool with no output schema, the description covers when to call, what each state means, the auth scope, and conditional parameters. It does not mention return values, but this is a low-risk, state-transition tool where the response is likely a simple acknowledgment; the essentials are present.

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 already 83%, and the description enriches the state enum by mapping each value to a moment ('running' when you start, 'shipped' once live, 'failed' with a reason). It also clarifies when asset_url and receipt_url should be passed, which complements the schema's parameter descriptions.

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 a specific action ('Carry a claimed job's state back') and defines the three state values with concrete meanings. It distinguishes what counts as 'shipped' vs. not, though it never names sibling tools like pick_up_job or ship_move, so the differentiation is 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?

The 'WHEN:' section explicitly tells the agent at which moments to call the tool and emphasizes reporting unprompted. It also provides a clear when-not-to-ship rule ('drafted, staged and awaiting review are not shipped'). It falls short of naming alternatives, but the timing guidance is strong.

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