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

The description extensively discloses behavioral traits beyond annotations: it is 'SERVER-DRIVEN and stateful', requires session_key reuse, returns 'added' or 'question_pending' statuses, and mandates asking the user EXACTLY one question at a time. This adds significant value over the minimal annotations (all false). It does not cover error handling or auth, but the essential stateful behavior is well explained.

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 every sentence earns its place. It opens with the purpose, then uses bullet points to separate the two call flows, ending with a critical warning about session_key. The structure is clear and front-loaded with the most important information, making it easy to parse despite the complexity.

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?

Given the tool's complexity (10 params, nested objects, no output schema), the description covers the key aspects: how to start, how to continue, and what responses to expect. It does not describe the contents of an 'added' response, but that is not essential for invocation. The reference to bk_operator_availability provides prerequisite context. It is reasonably complete, though a bit more explanation of the response structure would make it fully self-contained.

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?

With 100% schema coverage, the baseline is 3, but the description adds substantial meaning. It explains the role of session_key (omit on first add), pending_token for subsequent answers, the answer object structure, and that quoted_price comes from bk_operator_availability. It also clarifies the parameter groups for the two call modes, which is not evident from the schema alone.

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 clearly states the tool's core function: 'Add a product to the Bookeasy booking cart, OR answer a booking question.' It specifies the two distinct use cases and distinguishes itself from sibling cart tools like bk_cart_checkout and bk_cart_promo. The verb 'add' and resource 'booking cart' are 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?

The description provides clear workflow context: when to omit session_key for a new cart, how to pass initial parameters, and how to handle the question_pending flow by reusing session_key and pending_token. It references bk_operator_availability as the source for quoted_price. It does not explicitly mention alternatives or exclusions, but the context is clear enough for an agent to know when to use this tool versus others.

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