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

Adds substantial context beyond the annotations: the billing model ($0.02 per call, nothing on failure, $0.25 on completion) and the link lifetime semantics (countdown starts at `days`, then the test time limit runs). It also discloses that the email is sent in the business's name, an externally visible side effect. These are exactly the traits annotations cannot express.

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 with zero filler: action first, then link lifetime, then cost. Each sentence carries distinct, decision-relevant 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?

For a paid mutation with an external side effect and no output schema, the description covers cost, failure charging, delivery identity and link lifetime. The only gap is what the call returns (a send confirmation, the link, an assessment id), which an agent may want before chaining.

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 50%, leaving `days` and `applicant_id` undocumented in the schema. The description explains `days` precisely — the link is valid for that many days, after which the test's own time limit governs — which is meaning the bare integer/range does not convey. `applicant_id` is self-evident from the 'applicant' framing; `message` and `assessment` are already covered.

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?

Specific verb+resource: emails an applicant a personal link to a named assessment, sent under the business's identity. It is clearly separable from siblings like hiring_assessment_results or hiring_save_assessment, but it never explicitly contrasts itself with hiring_email_applicant or hiring_invite_to_interview, which are the closest neighbours an agent might confuse it with.

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 describes what happens when called but gives no when-to-use framing, no prerequisites (e.g. applicant must exist, assessment must come from hiring_list_assessments — that hint lives only in the schema), and no alternatives. An agent must infer the workflow position of this tool entirely from context.

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