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

Annotations already declare idempotentHint=true and destructiveHint=true, and the description adds real context beyond them: the prompt goes to the guest's own phone, nothing is charged until the guest approves there, and repeated prompts are suppressed. It does not explain what makes the call destructive or what happens if the guest declines, so it adds value without fully illuminating the side-effect risk.

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 sentences, front-loaded with the action and its precondition, then the prompt destination and charge behavior, then the optional override. Every sentence carries distinct information, though the parenthetical about the order result is slightly wordy.

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, the description carries the return-side burden and covers the key facts: the call triggers a prompt, not a charge, and it is not repeated. It omits failure modes (expired draftId, invalid number) that an agent would want before retrying, which keeps it below 5.

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 100%, so both parameters are already documented; the description only restates that mobileMoneyNumber overrides the number from the draft. It clarifies the override is exceptional ('Only to use a different...') but adds no format, normalization, or validation detail beyond the schema.

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 and resource ('sends the mobile money payment prompt for a delivery order') with the exact precondition that identifies the target state: order placed but unpaid, with payment required and a draftId from the order result. This cleanly separates it from siblings like place_delivery_order, confirm_delivery_order, and draft_delivery_order.

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?

Gives a precise triggering condition ('order result says payment is required and gives its draftId') and a repeat-call rule ('a prompt already sent is not sent twice'). It does not explicitly name which sibling to use for the adjacent cases (e.g., confirming or canceling the order), so it falls just short of full when/when-not routing.

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