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

The description discloses substantial behavior beyond annotations: links are verification-locked, a one-time code is sent to the recipient's contact on file, recipients with both email and phone appear as two entries, recipients with no contact method are omitted, and calling generates and persists links on first use. Annotations provide idempotentHint and non-read-only status, and the description aligns with them while adding rich operational detail.

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 long but every section earns its place: purpose, security model, response shape, edge cases, and state-changing behavior. It is front-loaded with the core purpose and then covers essential caveats in a structured, readable way. Nothing feels redundant.

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 uses only one parameter, has no output schema, and involves complex security behavior, the description is remarkably complete. It explains response fields, verification flow, duplicate entries for dual-contact recipients, omitted recipients, idempotency, and the sent-versus-draft restriction, leaving no critical gap for correct invocation.

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 schema already provides 100% coverage for the single documentId parameter. The description adds meaningful semantic constraint by specifying the document must be sent, not a draft, which goes beyond the schema's generic 'Unique identifier of the document' and helps the agent validate inputs before calling.

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 first sentence states a specific verb, resource, and scope: 'Get unique, self-distributable signing links for a document — one per recipient.' It clearly distinguishes this from generic link tools by emphasizing per-recipient, verification-locked links and manual distribution, which separates it from siblings like get_link or list_links.

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?

Explicitly states when to use the tool: 'Use this for signees created with disableInvitationMessage: true' or 'whenever the user wants to distribute a signing link themselves.' It also gives when-not guidance ('Only works on a sent document, not a draft') and names related alternatives like update_signee and revoking/resending the document for unrecoverable cases.

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