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

Goes well past the annotations (readOnly, non-destructive, open-world) by disclosing which sensitive PII is exposed — date_of_birth, gender, married status, personal email, phone, home address — and which fields are never returned (National Insurance numbers, payroll id, starter declaration, student-loan flags). That privacy profile is exactly the kind of behavioral context annotations cannot express and directly affects how an agent should handle the output.

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?

Two dense sentences plus the endpoint: purpose first, then the field inventory including the sensitive and excluded sets. Every clause carries information an agent would otherwise have to infer, and nothing is repeated from the schema or annotations.

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 carries the full burden of describing the return value, and it does so field by field, including negative space (never-returned fields). Pagination is covered by the schema, so nothing material is missing for a safe, correct call.

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%: page and per_page are fully documented in the schema, including the 1-25 cap and the "pass the previous reply's next_page" instruction. The description adds no further parameter meaning, so the baseline of 3 applies. It also does not warn that a whole-company listing may require many pages at 25 per page.

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 and resource ("List the company's team members (employees)") and then enumerates exactly which fields come back, so an agent knows precisely what the payload contains. The plural list framing plus the explicit field inventory distinguishes it from the singular charliehr_get_team_member sibling without needing to open either schema.

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 by the field inventory and the endpoint, but there is no explicit guidance on when to prefer this over charliehr_get_team_member for a single employee, or over charliehr_list_team_member_salaries / charliehr_list_team_member_leave_requests for related data. No exclusions or prerequisites are stated beyond the never-returned field list.

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