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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries the burden of behavioral disclosure. It adds meaningful context: this is an approval-based workflow (the admin must act), and until approved the worker cannot be assigned work, pull tasks, or read outside its sandbox. There is no contradiction with annotations, and the async-approval nature is a valuable behavioral trait beyond what structured fields convey.

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: a front-loaded audience constraint, the main action, parameter-passing guidance, and the pending-state consequence. There is zero filler, and the most decision-relevant information (sandboxed-only) appears first.

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 4-parameter tool with no output schema, the description covers audience, action, parameters, and post-request restrictions. Minor gaps remain: it never says what the response/return value is, and the approval being asynchronous is only implied by 'until approved' rather than stated directly.

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 50%, so the description must partially compensate. It clarifies target_agency_handle as 'target org handle or name,' flags message and requested_client_ids as optional, and adds the useful scoping meaning 'client UUIDs to be scoped to.' However, worker_id is not mentioned in the description, and the intended use of message (e.g., a note to the admin) remains 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+resource: 'Ask an organization admin to move this worker out of its single-tenant sandbox and into their org.' The scope is unambiguous and the opening constraint 'For sandboxed workers only' clearly differentiates it from siblings like request_decomposition, request_key_challenge, and submit_support_request.

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 description provides clear context for when to use the tool: only for sandboxed workers who need to be moved into an organization, and it warns that the worker is restricted until approved. However, it does not explicitly name alternatives or state when-not-to-use conditions, so it stops short of a 5.

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