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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), yet the description still adds real value: it discloses that results are permission-scoped by the Famly Public API token, that certain personal fields are withheld, and the non-obvious rule that pagination must continue past an empty page. The main omission is record cardinality/ordering behavior, which keeps it from 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?

Four short sentences, front-loaded with what the tool returns, followed by exclusions, the pagination rule, and the auth caveat. No filler or repetition; every sentence carries distinct information.

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 six parameters, 17% schema coverage, and no output schema, the description covers scope and pagination adequately but leaves half the parameters opaque and says nothing about return shape or page-size limits. It is a viable minimum, not a complete briefing for an agent building a filtered staff query.

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 only 17% — just `next` is documented in the schema — so the description must compensate, and it largely does not. includePast, includeFuture, pageSize, employeeIds and siteIds are never explained; a reader cannot tell whether includePast means former staff or historical date ranges. Only pagination via `next` is reinforced.

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 the resource and its scope: a staff directory with employment dates, plus an explicit field-level exclusion list (no home address, birth date, gender, telephone, photographs). That exclusion list usefully separates this from a full employee-profile fetch and from famly_list_employee_checkins. It never uses a verb ('list') and relies on the tool name for the action, which is the only reason it isn't a 5.

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 only actionable guidance is pagination: 'Continue using next, including after an empty page.' Nothing says when to choose this over famly_list_employee_checkins or famly_get_staff_hours_totals, and the semantics of includePast/includeFuture — the key selection decision here — go unmentioned. Sibling routing is left to inference from names alone.

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