List clients

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the safety profile is covered. The description adds genuinely useful disclosure not in the annotations: contact data (emails, phones, DOB, NI numbers) is gated behind include_contact_details and otherwise redacted, and it names the underlying endpoint GET /clients. It doesn't discuss paging behavior in prose (that lives in max_results), which keeps it below a 5.

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 sentences, zero filler, front-loaded with what a client is and what is returned, then filters, then the sensitive-data caveat. The middle filter sentence is dense but each clause maps to a real parameter.

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 and the sensitive-data gate, which is the main completeness burden for an 11-param list tool. Pagination semantics and continuation via next_page are left entirely to the schema, so the definition is near-complete rather than fully self-contained.

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% with 11 well-documented parameters, so the schema does the heavy lifting and the baseline of 3 applies. The prose recap of the filter surface adds confirmation but no syntax or format detail beyond the schema, and its 'sort by name or date' phrasing is looser than the schema's six-value sort_by enum.

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?

Names the verb (list) and resource (clients) and disambiguates the resource with the parenthetical 'the people being onboarded', which separates it from list_records and list_client_records. It also enumerates the returned fields (name, decision status, reference, retention date, timestamps), so an agent knows exactly what this collection contains.

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?

The description clearly states the usable filter and sort surface (fuzzy search, status, visibility, assignee, exact reference, deletion-date bucket, sort order), which tells the agent when this tool can answer a query. It stops short of naming the single-client alternative (get_client) or the condition that selects it, so it reads as strong context without explicit routing.

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