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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely new context: only opted-in operators are ever returned, so an empty result can mean 'not opted in' rather than 'no match' — a real behavioral trait. It omits pagination, result caps, and ordering, which matters for a search 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 tight sentences, front-loaded with what is listed before the return fields and filter rules. No filler. The only slight redundancy is repeating the profession list that the filter parameter also implies.

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?

With no output schema, the description compensates well by enumerating returned fields (slug, operator_id, display name, business name, city, profession, booking URL). Combined with strong annotations and full schema coverage, an agent can call it correctly; only pagination/limit and sort behavior are unaddressed.

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 would be 3. The description still adds value by specifying that filters match part of a value and are case-insensitive, which goes beyond the schema's examples and clarifies substring matching semantics. It does not state whether multiple filters AND together, a minor remaining gap.

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?

States a specific verb ('Lists') and resource (Mane operators), enumerates the professions covered, and names the scope condition (opted in to be found through AI assistants). Returned fields and the opt-in scope let an agent distinguish this directory search from get_operator, which clearly retrieves a single record.

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: no filters means browse the whole opted-in directory, optional filters narrow by city/profession. However, no alternative is named — nothing tells the agent when to switch to get_operator, list_services, or list_availability instead of searching here. That leaves the sibling routing to inference.

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