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

With no annotations, the description carries the full burden and does so richly: human-gated elicitation requirement, model cannot self-confirm, permanence of the delete, the code becoming reusable afterwards, ordered side effects (Stripe object then DB row), and the client-capability refusal behavior. This is behavior far beyond the bare name.

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 safety-relevant info (human-gated, permanent) is front-loaded and every clause carries weight, but the middle section is dense and run-on, stacking mechanism, capability gating, and side effects into long sentences. Slightly more structure would help without losing content.

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 permanent, human-gated mutation with no annotations, no output schema, and 4 parameters, the description covers safety, side effects, reversibility, dry-run semantics, and prerequisite discovery. Nothing an agent needs in order to call it correctly is missing.

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 0%, so the description must compensate: it explains dry_run (preview without touching anything), confirm_used (only for dry_run previews), and code (surfaced to the human with percent and redemption count). app_id is left to inference, which is the only gap in an otherwise strong compensation for zero schema documentation.

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 ('Delete one coupon from an app') and pins the singular scope, which distinguishes it from the sibling bulk_delete_coupon. The mechanism is spelled out ('removes the Stripe coupon object and then the `coupons` row... no orphaned Stripe object'), so an agent knows exactly what is destroyed.

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?

Explicitly routes the agent: 'Use list_coupons first to confirm the code,' use dry_run:true to preview, and confirms that non-elicitation clients are refused while dry_run still works anywhere. It also distinguishes confirm_used's narrow role ('only consulted for dry_run previews'), which prevents misuse.

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