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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description adds materially more by disclosing that real people are emailed, that a legally meaningful process begins, that user confirmation is mandatory, and that unknown option keys are rejected. It stops short of stating whether a duplicate call sends twice, which matters given idempotentHint=false, but the safety profile is otherwise well surfaced.

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 consequence and confirmation requirement are front-loaded, followed by prerequisites, option keys, and a compact call/response example. Every sentence carries operational information; nothing is redundant with the annotations or schema.

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?

Despite the nested, free-form options object, the description supplies the accepted shape and strictness rule, plus the workflow preconditions. Return values need no explanation because an output schema exists and the example already shows the { sent: true, … } shape.

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 calls options merely "Optional send options" with additionalProperties=true, so the nominal 100% coverage conveys almost nothing. The description compensates by enumerating the accepted keys (participants with {email, name, …}, document_recipient_emails, from_user_email, invite_message, expiration, automatic_reminders) and noting that anything else is refused — an agent could not construct a valid call without this.

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?

"Send a document to its participants for signature" gives a specific verb (send) plus resource (document) and the resulting state (signature request). It is clearly distinguishable from siblings like cancel_document, publish, or upload_asset, which involve different lifecycle stages or artifact types.

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 states explicit preconditions and sequencing: fetch the document first, confirm with the user, ensure the draft is complete, and tell the user who will receive it. This names the prerequisite step (the fetch sibling) and a hard gate (user confirmation) rather than leaving usage to inference.

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