Send a reminder

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

Annotations only say this is not read-only and not idempotent; the description adds the critical fact that the first invocation is effectively a dry run that returns a summary and confirmation code rather than sending. That hidden two-phase semantics is exactly the behavior an agent cannot infer from the structured fields, and it prevents accidental premature sends.

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?

Two sentences, both earning their place: the action is stated first, then the non-obvious two-step safety protocol. Nothing is redundant or buried.

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 annotations, a full output schema, and complete parameter coverage, the description's main obligation is the confirmation protocol, which it discharges well. It does not mention edge cases such as reminding a signer who already signed or permission requirements for an outward-facing email, leaving a minor gap.

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 100%, and the schema already documents the confirmation parameter's sequencing ('leave empty first; pass the code only after the user confirms') and the signer default. The description restates this flow but adds no new meaning about parameter formats or edge cases, so the baseline 3 is appropriate.

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+resource ('Email a reminder to sign'), which is unambiguous about the action. It does not explicitly distinguish itself from siblings like send_draft or contact_documents, so an agent must infer the boundary, but the core purpose is immediately clear.

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 gives explicit procedural guidance for the two-call protocol: the first call sends nothing, and only a second call with the confirmation code actually sends, after the user agrees. It stops short of naming alternatives (e.g., when to use send_draft instead), so it lacks exclusions, but the when-to-call-with-code condition is stated clearly.

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