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

Annotations only tell the agent this is a non-idempotent, open-world, non-destructive write. The description adds substantial unannotated behavior: the created offering is invisible until put_page links it, mixed mode/config combinations are rejected, validation errors name the offending field and are safe to retry, and a wrong timezone silently shifts all slots. That is exactly the kind of consequence-level disclosure annotations cannot carry.

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?

Front-loaded with the core action and mode split, then ordered by risk (publication, mode config, timezone, confirmation). Dense but every sentence carries an operational instruction; the imperative tone is appropriate for a write tool, though the confirmation and currency guidance is repeated in both the description and the pricing schema.

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?

Rich nested schema plus an output schema means the description need not explain return values, and it correctly focuses on preconditions, failure behavior, and user-confirmation duties. The one gap is that it never surfaces the mode-dependent required fields (schedule/durationMinutes in slots mode) at the description level, leaving mode branching entirely to the 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; the description still adds decision-relevant emphasis the schema buries in prose — the timezone is the seller's zone and drives every slot, and currency must be asked for, never defaulted to USD. It does not restate the mode-specific required fields (durationMinutes, schedule) at the top level, so the agent must still read the schema for mode branching.

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 and resource ('Adds something people can book') and immediately disambiguates the two modes: appointments on a weekly schedule vs. stays. It also distinguishes itself from the sibling that publishes it ('It is not on the page until a booking block places it there with put_page'), so an agent can separate create_booking_unit from put_page/update_booking_unit without reading schemas.

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 a clear precondition ('not on the page until put_page') and an explicit gating step ('show the person exactly what will be saved and get their explicit yes'). It does not name update_booking_unit as the alternative for modifying an existing offering, so the when-to-use story is clear but not exhaustive.

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