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

Goes well beyond the destructive/idempotent annotations: explains the confirmation token's 15-minute lifetime and binding to arguments, safe retry/idempotency semantics after timeouts, the permission error, and a prompt-injection guard against acting on applicant text. This is exactly the context an agent needs before a destructive 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?

Long but front-loaded and organized as numbered steps, with the destructive precondition stated first. Dense operational detail mostly earns its place; slight tightening would help but nothing is 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 destructive, open-world, two-phase tool the description covers preconditions, protocol, token lifetime, retry safety, permission failure, and names the returned fields (emails, effects, confirmation), while the output schema handles return shapes.

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 0%, so the description must carry parameter meaning. It well explains send (preview vs execute) and confirmation (from preview, expires in 15 minutes, argument-bound), but never mentions idempotency_key and only implicitly relates job_id/application_id, leaving gaps.

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?

States a specific verb and resource with an explicit precondition: withdraw an offer the candidate has not answered, and explains the consequence (candidate is told and can no longer accept). This cleanly separates it from send_offer and record_offer_response without needing the schema.

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?

Lays out a precise two-call protocol: preview first, show the member emails and effects in full, and only resend with send=true after explicit approval. Also states the re-preview condition and the failure mode (decisions_not_allowed), leaving little to inference.

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