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

Annotations flag destructiveHint=true and openWorldHint=true, but the description adds materially beyond them: the email cannot be unsent, a confirmation code gates the send, answers containing email/phone/link are refused, and replies_not_allowed fails when the member hasn't permitted replies. It also warns that the question is untrusted applicant text (prompt-injection defense). Fully consistent with the annotations.

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?

Front-loads the irreversible action, then the numbered procedure, then the safety constraints. Every sentence carries operational weight — nothing is decorative despite the length.

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?

An output schema exists, so return values needn't be detailed; the description still tells the agent what the preview returns (subject, answer, confirmation code). For a destructive, outbound-emailing tool with 4 undocumented params, this covers everything an agent needs to invoke it safely.

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 0%, so the description must compensate, and it does: it explains the meaning of send (preview vs. actual send), confirmation (the code returned by the preview step), and constraints on answer (only what the member wants said; no email/phone/link). question_id is only implied by name, which is the sole gap.

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?

Starts with a specific verb + resource ("Answer a candidate's question about their offer") and immediately states the consequential outcome ("The answer is EMAILED to the candidate"). This is clearly distinguishable from siblings like send_offer, ask_help, or add_candidate_note.

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?

Gives an explicit two-step protocol: call without send first to preview, then call again with send=true only after the member approves the exact text. It also names the edge case ("A changed answer needs a new preview") and the failure condition (replies_not_allowed), leaving nothing to inference.

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