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

Annotations cover idempotency, non-destructive nature, and open-world behavior, but the description adds substantial non-obvious context: city tax is already included (do not add it), unpriced stays are rejected rather than silently confirmed at 0.00 EUR, and payment is requested post-submission via secure link with a 7-day-before-arrival deadline and no cash. It does not describe the return payload, though no output schema 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 content is front-loaded with the core action and prerequisites before details. It is dense but each sentence carries operational value — no filler. Slightly long, but every clause addresses a real failure or workflow concern.

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 complex 11-parameter booking mutation with nested customer object and no output schema, the description covers prerequisites, validation behavior, tax handling, payment terms, and sandbox mode. The main gap is the absence of any description of what a successful booking returns (confirmation id, status).

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, but the description goes further: it explains that roomId is a room-type abbreviation code (not a numeric ID) with examples, and that addons use addonId from the get_addons catalog. These clarify semantics beyond the schema text, which repeats the same hints but the description ties them into the workflow.

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 opens with a specific verb and resource — 'Create a hotel reservation at Hotel Bergsonne Allgäu' — immediately distinguishing it from its sibling read-only tools (search_availability, get_price_quote, get_hotel_details, get_addons, get_fact_sheet). An agent can tell this is the write operation that follows the availability/quote tools.

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?

Explicit prerequisites are named: 'Call search_availability and get_price_quote for the same dates and room first.' It describes the failure mode (NOT_AVAILABLE / INVALID_RATE), routes to get_addons for addons, and explains the test flag for sandbox runs. This is textbook when-to-use and how-to-avoid-failure guidance.

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