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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the pagination contract (nextOffset until null), the fact that short pages are intentional and must not be treated as the end, and the default user scoping behavior. It doesn't describe the response shape, but with no output schema and a read-only list operation, the pagination behavior is the most important behavioral disclosure and it is present.

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 compact and front-loaded: the core action ('List draft documents with pagination') comes first, followed by a one-sentence definition of drafts, a routing pointer to get_draft, and a clearly marked PAGINATION section. Every sentence earns its place, and the critical pagination warning is highlighted with a label.

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 read-only list tool with 100% schema coverage and annotations covering safety, the description is nearly complete. It covers the core action, the draft concept, the sibling to use for inspection, and the pagination contract. The only minor gap is that it doesn't describe the response envelope (e.g., that the response contains drafts and nextOffset), but the pagination instructions strongly imply it, and the schema documents the offset parameter. This is a minor gap, not a blocking one.

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 documents all three parameters (limit, offset, userId) with descriptions. The description adds the pagination protocol ('follow nextOffset until it is null') and the short-page warning, which complements the offset parameter description. However, it doesn't add meaning beyond what the schema provides for limit and userId. Baseline 3 is appropriate when the schema does the heavy lifting.

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 verb and resource ('List draft documents') and clearly distinguishes drafts from sent documents by defining them as 'saved document configurations that have not been sent for signing yet.' This differentiates list_drafts from siblings like list_documents and list_templates without needing to inspect schemas.

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 explicitly tells the agent when to use this tool versus alternatives: 'Use get_draft to inspect a draft before updating, sending, or deleting it.' It also provides a clear pagination protocol with an explicit stopping condition ('follow nextOffset until it is null') and a warning about short pages, which is exactly the kind of usage guidance an agent needs.

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