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

Annotations already flag a non-read-only, open-world, non-idempotent send; the description adds substantial context beyond that: paid-account prerequisite, a 500/day cap, per-email cost of $0.02, one-time link behavior, and skip rules for already-confirmed or email-less people. This is exactly the pre-call context an agent needs for a billable outbound email action.

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?

Behavior and constraints are front-loaded and dense, but the $0.02-per-email cost is stated twice in slightly different words, wasting a sentence. Minor redundancy aside, no filler.

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 still covers targeting, skips, prerequisites, limits, and cost, but never says what the call returns (e.g., a count of emails sent vs. skipped), which is the one gap for a batch-send tool.

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?

The schema documents both parameters (name as a slug like ai-use-policy, people as person_id or work email). The description adds the important semantic that omitting 'people' defaults to the policy's full scope, which the schema alone does not convey.

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 opens with a specific verb and resource — email each person in a policy's scope a one-time confirmation link — and clarifies the read-and-confirm purpose. It is clearly distinguishable from siblings like hr_save_policy (authoring) and hr_policy_status (checking confirmations).

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 explains the two targeting modes (policy scope vs. explicitly named people) and the skip conditions. It doesn't explicitly name alternatives such as hr_policy_status for checking who has confirmed, so routing guidance is implied rather than spelled out.

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