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

With only a destructiveHint annotation, the description carries the behavioral burden and does so well: it explains that an agent cannot sign for a person, that workspace members receive an email to sign themselves, and that company approval happens automatically only after everyone else signs. It also discloses field-placement defaults and that a sealed PDF with an audit trail is produced once signing completes.

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 front-loaded with the core purpose and then layers in necessary details about signer roles, fields, and completion. It is dense but largely earns its length given the complexity of the tool, though it could be slightly more scannable.

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 complex, nested-parameter create tool with no output schema, the description covers the main workflow, signer modes, field placement defaults, and the post-completion check via "get-signature-request". It does not describe the immediate return payload or error conditions, but the schema itself documents key inputs like send_email and signer link/url behavior.

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%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: roles map to signer parts, fields can be anchored or placed on PDF signature boxes, and without "fields" owner-mode fields or a single signer's empty boxes are used. It does not document every parameter in depth, but it supplies useful operational context.

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 states a specific action and resource: asking people to sign a document, with the resulting signature request implied. It clearly differentiates the creation/request flow from checking status by naming "get-signature-request" as the follow-up tool.

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 substantial context on signer types and field placement, which helps an agent decide how to invoke it for recipients, workspace members, and company approval. It does not explicitly compare against alternatives such as create-document-link, but the usage context is clear and specific.

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