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

Annotations only cover openWorldHint=false and destructiveHint=false, so the description carries most of the burden. It discloses the delivery channel (user's phone), the ~5 minute response window, and the returned session id, plus the required follow-up polling step. It does not address auth/permission requirements, but the workflow disclosure is substantial.

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 tight sentences, front-loaded with the action and return value, then the mandatory next steps. No filler; each clause carries operational instruction.

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?

An output schema exists and the description still names approval_session_id as the return, and the workflow chain through status-checking to commit is fully spelled out. The only real gap is that neither description nor schema clarifies the two input parameters, leaving the calling contract under-specified.

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 0%, so the description must compensate for both parameters (draftId, companyId) and does not. It alludes to a 'sealed draft' but never explains what draftId or companyId identify, their UUID format, or whether they are optional (required count is 0, an ambiguity left unaddressed).

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 ('Send the trusted-device approval'), the resource ('sealed draft'), and the concrete output ('approval_session_id'). An agent can distinguish it from siblings like commit_transfer and approval_session_get_approval_session_status without opening any schema.

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?

Explicit sequencing: do NOT call commit_transfer yet, poll approval_session_get_approval_session_status when the user reports answering, and commit only on APPROVED. It names both the alternative tool and the condition that gates it, which is exactly the routing an agent needs.

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