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

Annotations only provide openWorldHint=false and destructiveHint=false, which don't indicate read-only behavior. The description compensates by disclosing that this is an action that sends an approval request, and it adds the 5-minute response window and the instruction to poll only after user confirmation. However, it doesn't describe side effects like what happens if the user doesn't respond or if the draft is invalid, leaving some behavioral gaps.

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 two sentences with no fluff. The primary action is front-loaded, and the usage guidance is concise. Every word earns its place, making it highly efficient for an agent to parse.

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?

The tool has an output schema, so return values are defined elsewhere. The description covers the workflow well: sending the approval, the user response window, and when to poll. It lacks explicit prerequisites (e.g., what makes a draft 'sealed') and potential failure modes, but for a simple mutation with a clear workflow, it is fairly complete. Given the minimal annotations, a 4 is appropriate.

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 explain the parameters. It only hints at draftId by mentioning 'sealed draft' but never explicitly states that draftId refers to the sealed draft, and companyId is not mentioned at all. With both parameters having no descriptions in the schema, the agent is left to infer their meanings, which is a significant gap.

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 the action: sending a trusted-device approval for a sealed draft to the user's phone. It distinguishes itself from the sibling approval_session_get_approval_session_status by explicitly mentioning that polling is done separately. The verb 'Send' plus the resource 'trusted-device approval for a sealed draft' makes the purpose unambiguous.

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 gives explicit guidance on when to poll: 'Poll approval status with get_approval_session_status only when the user says they have answered.' This clearly differentiates when to use this tool versus the polling tool. It also implies the timing (within ~5 minutes) for user response, providing a concrete usage scenario.

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