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

Annotations already declare non-read-only, non-idempotent, open-world, non-destructive, so the safety profile is partly covered. The description adds genuinely non-structured facts: billing at $0.02 per call with no charge on failure, and that replies bypass the sender and land on the careers page's reply_to — both decision-relevant for an agent. It stops short of stating permissions, throttling, or whether the send is immediate vs scheduled.

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?

A single front-loaded sentence with the verb and resource first, followed by the cost and reply-routing caveats in a compact parenthetical. Every clause (identity, reply_to, use cases, price) carries information; 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?

For a no-output-schema side-effecting send with only 4 parameters, the description covers the two things an agent most needs to decide and act: what the message represents and what it costs. The remaining gap is invocation detail for subject/text and what a successful call yields, but those are modest against a short, well-scoped 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?

Schema description coverage is only 25% (just by_person), so the description needs to carry weight for applicant_id, subject, and text — and it says nothing about any of them (no id validity rule, no subject/text limits or tone guidance). It only gestures at applicant_id via "an applicant" and at the AI-disclosure line via "in the business's name," which the schema already documents more precisely.

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 ("Email an applicant") plus useful framing: sent in the business's name, replies routed to the careers page's reply_to, and the three candidate message types (interview invitation with booking link, next step, kind no). It never names a sibling, though — notably hiring_invite_to_interview, which appears to overlap with the "interview invitation with a booking link" case, so the agent gets no explicit differentiation.

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 enumerated scenarios (rejection, next step, interview invite), which gives a reasonable sense of when to reach for it. But there are no exclusions, no prerequisites, and no pointer to the overlapping sibling hiring_invite_to_interview or to email_send, so an agent must infer which tool to use.

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