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

Goes well beyond the destructiveHint/idempotentHint annotations, disclosing skip-aheld-phone behavior, whole-call rejection on bad phones, post-hoc do-not-call/duplicate flagging in validation_summary, the returned insert count and total, and the reassurance that it places no call. Consistent with destructiveHint=true.

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-loads the DRAFT precondition and packs real information into every sentence with no filler. Slightly dense, but each clause earns its place.

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?

With no output schema, the description still explains the response (inserted count and campaign total) and where validation flags surface. For a mutation tool with a precondition, that covers everything an agent needs to call it correctly.

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 100%, so the baseline is a 3, but the description adds value the schema doesn't express: contact_rows and contact_ids are mutually exclusive ('one of them') and the 2000-at-a-time limit is enforced. It also clarifies phone-dedup semantics.

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 (add contacts to a voice campaign) plus a hard precondition (must be DRAFT, an outbound AI campaign). Easily distinguished from siblings like remove_voice_campaign_contacts and clone_voice_campaign.

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?

Explicitly names the when-not (not scheduled, running or archived) and provides the concrete alternative for a scheduled campaign (clone it and add to the clone), implicitly pointing at clone_voice_campaign. Nothing left to inference.

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