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

Adds real behavior beyond the annotations (destructive/openWorld/non-idempotent): draft state, no dialling on creation, consent prerequisite, and calling-window/country-code mechanics. One concern: "Up to 10 calls at once, 5 attempts, retry after 5-1440 minutes" reads as hard limits while the schema defaults are 1 concurrent, 2 attempts, 60 minutes — this could mislead an agent about the effective values.

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?

Front-loaded with the operation and the most important constraint (draft, nothing dialled), then dense detail on window/country/personalization/limits. A single long paragraph with heavy parentheticals is slightly harder to scan, but little is wasted.

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 14-parameter mutation with a nested object, no output schema, and zero schema description coverage, the description covers the structurally tricky parameters but leaves several behavioral knobs (machine_action/message, concurrency) unexplained and the limits inconsistent with defaults. Adequate, not complete.

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 0% across 14 params, so the description carries the burden and does explain voip_campaign_window's shape, voip_campaign_country's 0-prefix completion rule, id-vs-uuid alternatives, and {name} substitution. However, voip_campaign_machine_action, voip_campaign_machine_message, voip_campaign_title, and max_concurrent get no explanation, and the attempt/retry numbers conflict with schema defaults.

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?

States a specific verb and resource ("Creates a DRAFT outgoing call campaign") plus scope (number/assistant by id or uuid, result contains id and uuid). The draft/not-dialled framing also implicitly separates it from start_voip_campaign and place_voip_call.

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?

Clearly establishes the lifecycle position: this only creates a draft, nothing is dialled until started, and starting requires an explicit yes plus merchant confirmation of consent in the panel. It doesn't name sibling tools explicitly, so it falls short of a 5, but the context for when to use it is unambiguous.

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