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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes further by stating the concrete blast radius ('codes stop working immediately'), the irreversibility, and the human-approval gate. It also discloses the underlying two-step GET-then-DELETE call pattern, which no structured field conveys.

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 compact sentences, front-loaded with the WRITE marker and the irreversible consequence before the procedural instructions. No filler or repetition of the schema.

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 two-parameter destructive tool with no output schema, the description covers the safety gate, the side effects, and the call sequence. It stops short of saying what is returned or how failures (e.g., coupon not found, already deleted) are surfaced, a minor omission given idempotency is annotated.

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 100%, so both coupon_id and confirm are formally documented. The description still adds semantic weight by tying confirm: true to the approval workflow rather than treating it as a bare boolean, though it adds nothing about identifier format or behavior on an invalid id.

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?

Opens with a specific verb and resource ('permanently delete a coupon from the live GivingFuel account'), scoping it as a write against production data. It also names the sibling read tool (givingfuel_get_coupon) whose output should precede it, so an agent can place it in the catalog 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?

Gives an explicit prerequisite sequence: call givingfuel_get_coupon, show the user the coupon, obtain approval, then invoke with confirm: true. It also implies when not to call, since the destructive effect 'cannot be undone' and codes stop working immediately. The alternative (reading instead of deleting) is named directly.

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