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

Annotations already signal destructive and idempotent, but the description goes further: repeat cancels are refused and never trigger a second refund, Stripe refunds follow the host policy, Bearer auth is required, and the call is rate-limited per token. No contradiction with annotations exists.

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 dense but well-organized: core action first, followed by exclusions, alternatives, prereqs, behavior, and parameter clarification. Every clause earns its place; the only minor cost is length, but that length is justified for a destructive financial tool.

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 destructive, refund-triggering tool with auth constraints and token pairing, the description covers when to use it, prerequisites, behavioral idempotency, parameter provenance, and required credentials. The presence of an output schema means return-value documentation is not the description's burden; nothing needed for correct invocation 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 100%, so the baseline is 3, yet the description adds meaningful guidance beyond the schema: reservationId must be a booking UUID from specific sibling tools and never a propertyId, guestToken must match the exact token issued at creation and is not substitutable by a Bearer token, and an omitted reason shows 'Cancelled via MCP' to the host.

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 uses a specific verb-resource pair — 'Cancel a confirmed booking' — and adds the refund behavior. It also distinguishes itself from hemmabo_booking_reschedule by naming the condition that selects each tool, making sibling differentiation explicit.

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?

It gives explicit when-to-use ('guest explicitly requests cancellation'), when-not-to-use ('pending/unpaid bookings'), and a named alternative ('hemmabo_booking_reschedule'). It also provides a prerequisite step ('read cancellationPolicy from hemmabo_booking_status') and auth/rate-limit expectations, leaving nothing to inference.

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