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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is known. The description adds genuinely new behavioral context: results depend on catalog selections, nothing is held until book confirms, and a repeat pattern 'may change the price'. That price-affecting side effect of an otherwise read-only query is exactly the kind of thing annotations cannot convey.

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?

Usage guidance is correctly front-loaded, and every clause carries some intent, but the prose is telegraphic and hard to parse ('For the selections from catalog: live open times, the same for every kind of business'). Fragments like 'A person is optional: who is a wish, only_who makes it firm' force re-reading and bury key semantics.

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 10-parameter, no-output-schema tool with annotations covering safety, the description covers the essentials: when to call, the catalog dependency, no-hold semantics, the request-only branch, and price sensitivity of repeat. It does not describe the shape of the returned times or how many are returned, and it references a request_only flag that is absent from the schema, which is a real gap.

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 60%, so the baseline is 3. The description explains the who/only_who wish-versus-firm distinction and that quantity is party size for a table or class, but these points largely restate what the schema's own field descriptions already say. It adds nothing for date, days, repeat, start_after, finish_by or time_of_day, leaving those to 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 states a specific verb and resource ('see when they can book', 'live open times') and ties it to selections from the catalog, so an agent knows this is an availability query. It distinguishes itself from book ('Nothing is held until book confirms') and request_booking. The clause 'the same for every kind of business' is vague filler, but the core purpose is unambiguous.

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?

It gives explicit triggers ('when the user wants to see when they can book', 'when an owner asks when they can fit a job in—pass their own business id') and names the alternative for the no-commitment case (use request_booking). It also points to book for actually holding a slot. The guidance is slightly undercut by the fact that request_only is not an actual parameter in the schema, making that routing condition ambiguous.

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