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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavioral context: the result ordering rule (town area-page matches with relation 'in'/'serves'/'nearby' and miles, then filmed-first), the caveat that badges are self-reported, and the per-page limit behavior. That is real disclosure beyond structured fields.

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 purpose and scope lead the description, followed by return fields and ordering rules, with formatting requirements last. It is information-dense but somewhat long; a couple of clauses (e.g. the full field list) could be tightened without losing meaning.

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 usefully enumerates returned fields (name, bio, skills, prices, reviews, filmedTheirWork, workVideoCount, vouches, service area, profile URL) and explains ranking, so an agent can interpret results. The one gap is that no pagination mechanism beyond `limit` is described, so multi-page retrieval is ambiguous.

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 description coverage is 100%, so the baseline is 3, but the description adds usable detail: it reiterates and exemplifies the slug/state/city formats and points to list_service_categories for slug lookup, plus clarifies that limit controls results per page. It does not explain how to page beyond the first request, which caps this at 4.

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 names a specific verb ('Find', 'Searches locals on GigNGo') and a concrete resource (real people offering home jobs/errands), with enumerated examples of the service types. It is clearly distinguishable from sibling read tools like get_worker_profile (single person) and browse_open_tasks (tasks, not people).

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 routing guidance for the service parameter: 'Use list_service_categories first if you are unsure of the service slug.' However, it does not contrast itself with neighboring discovery tools such as get_worker_profile or find_work_clips, so the when-not-to-use case is left implicit.

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