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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds value beyond them: the result is a draft rather than a sent broadcast, the required auth tier is `full_access`, and two preconditions on inputs must hold. It omits what happens on invalid domain/audience or what the created draft contains.

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?

Compact and front-loaded: purpose, then output state, then constraints, then auth/endpoint. The opening sentence only restates the tool name and title, which is the one wasted line in an otherwise tight description.

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 an 8-parameter mutation with 25% schema coverage and no output schema, the description covers auth and two key input constraints but says nothing about the remaining optional body fields or what a successful response returns (e.g., a broadcast id for later send_broadcast). Adequate but with clear gaps.

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 only 25%, so the description must compensate. It adds real semantics for two of eight params — `from` must belong to a verified domain and `audience_id` must be an existing audience — but leaves `html`, `text`, `preview_text`, `subject`, and `name` unexplained beyond the schema's own types and limits.

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 ('Create a broadcast') and immediately clarifies the output state ('Creates a draft'), which separates it from send_broadcast and update_broadcast in the sibling list. It does not explicitly name those siblings, so it stops short of a 5.

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 concrete preconditions that determine when this call will succeed: a `from` address on a verified team domain, an `audience_id` from the caller's audiences, and a `full_access` API key. The 'creates a draft' framing implies sending is a separate step, but no alternative tool is named and no exclusions are stated.

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