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

Adds substantial context beyond annotations: blast radius (every subscribed contact in the audience), status lifecycle (queued → sending → sent), and the auth requirement (full_access API key). Annotations already flag openWorld and non-idempotent; the description adds the irreversible audience-wide reach and the human-in-the-loop expectation. It does not say whether a bad send can be recalled or what the response contains, which keeps it below a 5.

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 action, then prerequisites, then the API endpoint reference — each sentence carries weight. The 'needs html or text' line is the one piece that doesn't map onto this tool's parameters and slightly muddies an otherwise tight spec.

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?

No output schema exists, and the description fills that gap by describing the resulting status progression; it also covers the readiness prerequisite and the permission level. For a high-consequence, non-idempotent send operation, an agent has everything needed to call it safely.

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 50%, and the description compensates usefully: it explains what omitting scheduled_at does and that the target is a draft broadcast. However, the mention that 'The broadcast needs html or text' refers to fields not present in this tool's schema and it never clarifies that id is the broadcast UUID, so some ambiguity remains.

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+resource ('Send or schedule a broadcast') and immediately clarifies the effect: queues a draft for delivery to every subscribed contact of its audience. This distinguishes it from create_broadcast and update_broadcast in the sibling list, since those prepare the draft rather than deliver it.

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 prerequisite sibling ('Run get_broadcast_readiness first') and adds a user-confirmation gate, plus the key branch condition: without scheduled_at it sends immediately. An agent knows both the call order and the two modes without opening any schema.

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