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

Annotations only flag this as a destructive, idempotent, non-open-world write; the description adds the auth requirement, the partial-merge behavior that determines what gets overwritten, the per-day data shape, the add-vs-remove semantics of closed_dates and reopen_dates, and the fact that routing changes from the next call. It also describes the return ('the saved week as read back'). That is substantive behavior beyond the structured fields, and it does not contradict the destructive hint.

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 definition is front-loaded with the purpose, then the auth requirement, the merge rule, the value shape, and the return, in the order an agent needs them. Every sentence carries distinct information, and the parenthetical example and quoted date make the constraint concrete without padding.

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?

This is a five-parameter nested-object mutation, and the definition covers the pieces that matter: auth, overwrite semantics, nested value format, list add and remove behavior, and when the change takes effect. Since an output schema exists, the brief return note is sufficient, and nothing an agent needs to call it correctly is missing.

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 already 100%, so the baseline is 3; the description earns above that by restating the day object as { open, close } or { closed: true } in 24-hour time and clarifying that closed_dates adds while reopen_dates removes, which is not obvious from names alone. It adds no guidance on business_id or timezone beyond the schema, so a 5 is not warranted.

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?

A specific verb plus a precisely enumerated resource ('opening hours, timezone, or one-off closed dates'), reinforced by a concrete example ('we're closed Friday the 27th') and a dashboard analogue. Nothing about it could be confused with the setup or rules siblings; the scope is unmistakable. Differentiation is implicit in the resource breadth rather than by naming a sibling, but the definition still lets an agent route correctly.

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 an explicit prerequisite ('admin role required') and a clear merge condition ('Only the days you pass change; every other day keeps what it had'), which tells the agent how to safely make partial updates. It also states that call routing picks up the new hours from the next call, which is the timing context an agent needs. It never says when to prefer another tool (e.g. set_up_business) or when not to use it, so it stops short of a 5.

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