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

Beyond annotations, it discloses the dry_run contract (advisory estimate, reserves nothing, may differ from later execution), the draft safety guarantee (never sends), and the `removed` counts for filtered recipients. This materially expands on readOnly/destructive/idempotent hints without contradicting them.

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 compact sentences with the primary action first, return behavior second, and safety/dry-run semantics third. No filler; every sentence carries a distinct piece of information an agent needs.

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?

Coverage is strong for a draft-creation tool: it states what is created, what is returned, and how the safe dry-run mode differs. It loses one point only because there is no output schema and the full success response (e.g., campaign identifier/status) is not described.

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 low (14%), but the description adds meaning for the main non-obvious parameters: sequence steps, {{first_name}}-style variables, leads, sending window, and dry_run behavior. The remaining params are either named clearly in the schema or constrained in a self-documenting way (e.g., `stop_on_reply` has `const: true`).

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 action and object ('Create a draft email campaign') and enumerates the core content (sequence steps, variables, leads, sending window). It also disambiguates from `launch_campaign` by explicitly saying drafts never send and launch is a separate confirmed action.

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 establishes when this tool is appropriate: for creating a draft with optional dry-run estimation, and it clarifies that launching is not part of this call. It does not enumerate explicit exclusions or compare against every sibling, but the launch/draft distinction gives a clear routing signal.

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