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

Annotations only supply the generic readOnlyHint=false/destructiveHint=false pair, so the description carries the real burden and does so: it discloses that approval is required by an admin and that until approval the worker cannot be assigned work, pull tasks, or read outside its sandbox. It does not say how approval is surfaced or how to check status.

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?

Five short sentences, no filler: precondition first, then the action, then the inputs, then the consequence, then a doc link. The most decision-relevant constraint is front-loaded.

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?

With no output schema and thin annotations, the description does the heavy lifting on preconditions and consequences, which is what an agent needs before calling. It omits the post-call lifecycle (how approval is detected, whether the request is synchronous), a minor gap for an async approval flow.

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 50% (message and requested_client_ids have no schema descriptions), but the description compensates by naming all three optional/required inputs and explaining that the client UUID list is "to be scoped to," which the schema does not convey. It leaves the exact relationship between target_agency_handle slug vs. name slightly 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?

The description states a specific verb and resource: ask an org admin to move a sandboxed worker out of its single-tenant sandbox and into their org. The opening scope guard ("For sandboxed workers only") immediately separates it from worker-management siblings like archive_worker or update_worker.

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 precondition is explicit ("For sandboxed workers only") and the approval gate is described, giving the agent a clear trigger condition. It does not name an alternative tool or say what to do instead when the worker is not sandboxed, so it stops short of the top score.

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