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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and the description adds genuinely useful side-effect scope: the call creates a pending draft only, no email reaches signers, and the returned review_url expires in seven days. What it omits is whether repeated calls create duplicate drafts (relevant since idempotentHint is false) and what happens after expiry.

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?

Three short sentences, no fluff, and the most decision-relevant fact — that nothing is sent and a review_url comes back — is front-loaded. The expiration detail is tacked on at the end where it belongs.

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?

There is no output schema, so the description carries the return value, and it does: review_url plus its seven-day lifetime, and the crucial gap that the agent never handles the PDF. An agent could still be surprised by duplicate drafts on repeat invocation or by what a lapsed review_url means, which keeps it off a 5.

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 description coverage is 100%, so the schema already explains label, message, signers (1–10, signing order), in_order, expiry_days and remind_every_days. The description adds no parameter-level meaning beyond that baseline, which is acceptable but not additive.

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?

Opens with a specific verb and resource ("Prepare a signature request") and immediately scopes what it does *not* do — nothing reaches signers, the human sends from a review_url. That two-phase framing distinguishes it from siblings like send_request or create_request_page without the agent needing to open any schema.

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?

Clear usage context: call this when you have signers but not the document, then hand the review_url to the human who adds the PDF and presses Send. It does not explicitly name an alternative (e.g. send_request) or state exclusions, so it falls short of full routing guidance, but the when-to-use is unambiguous.

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