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

Annotations only indicate the tool is not read-only, not idempotent, and not open-world, but the description goes far beyond that. It discloses the full confirmation protocol, including the elicitation card / CONFIRMATION_REQUIRED return path, the confirmation_token fallback, timeout behavior, and the audit_trail_offer hint. It also explains the MISSING_SIGNATURE_FIELDS failure mode and the inability to add signers through this call. No contradiction with the annotations exists.

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 tightly organized and every sentence earns its place. It uses an IMPORTANT callout, a numbered confirmation flow, and a post-send audit trail tip. The length is justified because it covers several failure modes and edge cases that an agent would otherwise encounter.

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 no output schema and eight parameters, the description provides a complete decision procedure: preconditions, confirmation flow, token fallback, error handling, and response hints. It explains what the agent should do on each possible return path instead of leaving the tool to fail ambiguously. The only minor gap is full schemas for account_id and email_content, but their role is inferable from context.

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 only 13%, and the description compensates heavily for the most confusing parameter: emails 'does NOT add or configure signers — it only targets manual (copy-only) recipients.' It also precisely defines the confirm/confirmation_token contract, including reusing the same envelope_id/item_id/emails/email_content/account_id on the confirmed call. It does not add much detail about account_id or email_content, but the critical semantic traps are documented.

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 the precise operation: 'Send a signature request for a Getsign envelope and Monday item.' It names the concrete resource pair and immediately clarifies what the tool does. It also distinguishes itself from siblings by explaining what it does not do, such as configuring signers, which is handled upstream.

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 gives explicit preconditions: check getsign_get_signer_data first, offer getsign_get_document_url(action='preview'), and never gate sending through free-form chat. It also specifies the fallback path when no signers exist or MISSING_SIGNATURE_FIELDS occurs: call getsign_get_document_url(action='edit') and share the editor URL. Clear exclusion rules are provided, such as not passing emails as a workaround for missing signers.

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