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

With annotations already declaring a non-read-only, non-destructive, non-idempotent, closed-world mutation, the description adds genuine substance: what is returned (reservation id or plain-language error), the capacity-refusal condition, slot-alignment rules under shared=true, and a prompt-injection warning for `untrusted` text. The gap is retry behavior — idempotentHint=false means a repeated call books twice, which is never mentioned.

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?

Purpose and return value are front-loaded, and every clause carries information about a real failure mode. The shared-slot sentence is dense and run-on, packing three separate rules into one comma chain, which slightly hurts scannability.

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 6-param mutation with no output schema and no enum constraints, the description covers return values, the main refusal modes, and the injection hazard — enough to call it correctly the first time. Missing pieces are idempotency on retry and where roomId comes from, both of which matter for a non-idempotent write.

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 17% (workspaceId is the sole documented param), so the description must carry the load. It does well on `attendees` (seat count, default 1, capacity ceiling) and on how `startUtc` must align to slotMinutes from opening time, but says nothing about `roomId` (presumably from list_rooms), `title`, or why `endUtc` must match a whole slot boundary.

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?

Opens with a specific verb+resource ("Book a space for a time window") that an agent can act on immediately, and the return statement clarifies it creates a single reservation. It does not explicitly name how it differs from create_recurring_reservation or modify_reservation, though "for a time window" implies a one-off booking.

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?

Usage is implied rather than stated: the description covers what happens on unavailable slots and capacity overflow, which hints at preconditions, but never says to check_availability first or to use create_recurring_reservation for recurring series. An agent must infer sibling routing from the sibling names alone.

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