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

Adds behavioral context annotations cannot express: each answered call bills both telco and AI usage from the wallet, so cost scales with contact count. Annotations only say openWorldHint=false, idempotentHint=true, destructiveHint=false — none of which conveys the financial blast radius. The human-confirmation requirement is also disclosed here rather than in structured fields.

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?

Two sentences, with the money risk front-loaded in capitals before the mechanics, and the safety gate last. Every clause carries distinct information — cost source, scope, and prerequisite — with no filler.

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 two-parameter mutation tool with no output schema, the description covers the risk profile, the scope, and the required precondition adequately. It leaves implicit that the agent should retrieve the contact count via get_broadcast before confirming, and says nothing about what the call returns or whether it can be undone via pause_broadcast.

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%, with broadcast_id documented as a broadcast UUID and the purpose field fully described. The description reinforces that the broadcast identity and its contact count must be known before calling, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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?

Names a specific verb and resource: 'start dialing every queued contact in the broadcast'. The scope ('every queued contact') is precise and immediately tells an agent this is a bulk operation, not a single dial. It does not differentiate itself from sibling resume_broadcast or start_dialer_campaign, which is the only gap.

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?

Gives an explicit, unusually strong usage gate: 'NEVER call this without explicit human confirmation naming the broadcast and its contact count.' That is a clear when/when-not condition. It stops short of naming the sibling tools to use instead (resume_broadcast, get_broadcast to fetch the count), so not a full 5.

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