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

With no annotations provided, the description carries the full burden. It discloses the creation behavior, the pending_confirmation result state and the confirmation_url field, and warns against inventing guest details. It doesn't mention idempotency/retry behavior, but the idempotency_key parameter description covers that. Some notes on side effects or duplicate prevention could strengthen it, but the description is already unusually transparent for a creation tool.

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?

Three sentences, each earning its place: what the tool does, the critical usage protocol, and the expected result handling. Front-loaded with the purpose and immediately actionable instructions. No fluff or repetition.

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 9-parameter creation tool with no annotations and no output schema, the description gives the essential protocol: source of start, real guest data policy, and post-creation behavior. It doesn't enumerate every parameter (e.g., slug, party_size, notes, source), but the schema and parameter descriptions cover some of those. The pending_confirmation/confirmation_url guidance is especially valuable in the absence of an output schema. Missing: no explicit statement about idempotency/duplicate retries, though the parameter description covers it.

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 only 33%, with only start, source, and idempotency_key getting descriptions in the schema. The tool description compensates by explaining that start must be copied from check_availability, that guest name/email/phone must be real (collected from the person), and that pending_confirmation maps to confirmation_url. It doesn't explain party_size or notes semantics, but the description's coaching on guest details adds real meaning beyond the schema.

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 'Create a real reservation,' a specific action+resource. It also distinguishes itself from siblings by referencing check_availability, making clear this is the booking counterpart to the availability-checking tool. No ambiguity about its purpose.

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 gives strong usage guidance: use a start value from check_availability, never invent guest details, ask for real name/email/phone first, and handle pending_confirmation results by showing confirmation_url. It doesn't explicitly say 'do not use this tool for checking availability,' but the reference to check_availability and the 'real reservation' framing make the boundary clear. Loses one point for not explicitly naming when to use a sibling instead.

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