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

Annotations only supply destructiveHint=true, so the description carries most of the behavioral burden and delivers real value: 'Does NOT record any payment' and 'Reversible with bookeo_cancel_booking' tell the agent about side effects the annotation cannot express. The statement that a hold is released on success is also useful. It does not mention permission requirements or rate limits, and the 'reversible' claim sits somewhat uneasily beside destructiveHint=true, though it is clarifying rather than contradictory.

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?

Four dense sentences, front-loaded with the core action and customer choice, then constraints, then side effects. No filler, though the sentences are tightly packed and the product-type rules could be slightly more scannable.

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 18-parameter nested-object mutation with no output schema, the description covers the critical decision points (which customer field, which scheduling field per product type, hold conversion, no payment, reversibility). It omits what the call returns (e.g. the new booking id) and any confirmation/notification defaults, which an agent would benefit from knowing given there is no output schema.

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, and the description adds cross-parameter conditional logic the schema cannot express: product-type-dependent eventId/startTime requirements and hold conversion via previousHoldId. Many of the 18 parameters (options, resources, notify flags, promotionCodeInput, mode, externalRef) receive no description-level treatment, but the schema covers them individually.

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 ('Create a confirmed booking') plus the two mutually exclusive customer paths (existing customerId vs new customer object). It also distinguishes itself from adjacent tools by naming the availability tools, bookeo_create_hold and bookeo_cancel_booking, so an agent can place it in the workflow without opening a 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 concrete conditional routing: fixed/fixedCourse products need an eventId from the availability tools, flexibleTime products take eventId or startTime, and previousHoldId converts an existing hold. It names the related tools but never states an explicit when-not-to-use condition or a fallback if the slot is unavailable, so it stops short of full 5-level guidance.

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