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

The description goes beyond annotations by detailing rate-limiting behavior (429 with Retry-After, silent skipping for envelope form), error responses (409 for non-pending states), and cumulative effect on auto-cadence. It also explains that the tool sends real emails to third parties, which isn't captured by annotations. The only gap is that it doesn't explicitly state whether the action is reversible or if it triggers any side effects beyond emailing, but given the existence of annotations (destructiveHint false, readOnlyHint false), this is still quite transparent.

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?

The description is dense with information but is roughly 170 words, covering purpose, parameters, rate limits, error handling, and permissions. It's longer than ideal, but every sentence adds value—no fluff. Could be slightly trimmed for readability, but it earns a high score for efficiently packing actionable details.

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?

Given the tool has no output schema, the description compensates by explaining what happens (email sent) and what responses to expect (429, 409, silent skip with skipped_reason). It covers permissions (requires signatures:write scope) and error cases. A small improvement would be noting the exact retry-after header format, but overall it feels complete for a nudge tool of moderate complexity.

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?

The input schema already covers both parameters with descriptions, achieving 100% coverage. The description adds context about what each parameter does (single vs. envelope-level nudge) and usage constraints (exactly one), which is useful but not transformative beyond the schema's own descriptions. 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 clearly states the tool resends signature invitation emails, distinguishes between reminding a single signer (via signatureRequestId) versus an entire envelope (via envelopeId), and explicitly notes there is no separate envelope-reminder tool. This differentiation from sibling tools like create_signature_request or get_signature_request is strong.

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 explicitly tells when to use each parameter ('supply exactly one; there is no separate envelope-reminder tool'), explains rate limits (429 REMIND_TOO_SOON, implicitly capped at one per hour), and clarifies edge cases: pending-only reminders, skipped sequential recipients, and the effect on the auto-cadence cap. It also warns that real emails are sent, providing essential context for safe invocation.

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