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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's added value is in consequences: the held time is freed at once and the pay link stops working. That is real context beyond the annotations, though it doesn't address what happens if the draft was already cancelled or already expired.

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?

Two sentences, zero waste. The core action and its precondition are front-loaded, with the exclusion and alternative channel following immediately after.

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 mutation with no output schema, the description covers permission/precondition, side effects and the escalation path. Only the response shape (e.g., what confirming value comes back) is left unaddressed, which is a minor gap.

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% and both parameters (ref, poll_key) are documented in the schema, so the baseline of 3 applies. The description adds no format or provenance detail beyond what the schema already states.

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+resource ('Cancel a draft') plus the exact precondition ('the customer has NOT paid for'), and distinguishes itself from reschedule_booking and create_booking_draft. An agent can tell immediately whether this is the right tool without opening the 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?

Explicitly says when to use (unpaid draft) and when not to (a paid or confirmed session), and names the alternative channel for the excluded case ('refunds and the 24-hour rule are handled by ElloMind on WhatsApp'). This is exactly the when/when-not/alternative pattern.

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