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

Annotations provide readOnlyHint=false and destructiveHint=false, but the description adds valuable behavioral context: 'Effect: workspace-change', required permission, and idempotency retry guidance. This goes beyond the annotation hints and offers a clear side-effect profile, though it does not describe return values or validation behavior.

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?

The description is four short sentences, each with a purpose: defining the action, noting side effects, explaining idempotency, and giving permission/reference. No wasted words or redundant information.

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?

Given the complex nested body schema, the description adequately covers purpose, side effect, permission, and idempotency, and points to an API reference for deeper detail. However, it does not explain when to use this over similar create tools or clarify that the draft is not sent automatically, though 'draft' implies that. The presence of output schema compensates for not describing return values.

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% (both body and idempotency_key have descriptions). The description itself adds minimal parameter-level detail beyond the schema, merely restating that the idempotency key can be retried, which is already in the schema. It correctly does not duplicate schema content.

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?

The description clearly states 'Creates a broadcast draft in the authenticated workspace', using a specific verb and resource, and explicitly notes 'draft' to distinguish from send/schedule tools. This differentiates it from sibling tools like broadcasts_send and broadcasts_schedule.

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?

The description provides context that this is a create operation and mentions permission and idempotency, but does not explicitly state when to use this vs alternatives (e.g., broadcasts_update, broadcasts_send). It does not reference sibling tools or give exclusion criteria, leaving usage inference to the name.

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