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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered elsewhere. The description goes beyond that by naming the exact blocker codes returned and by defining the empty-list case as the success signal, which is genuinely useful behavioral context. It stops short of saying whether results are cached or whether readiness can be stale relative to a concurrent update.

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, front-loaded with the action and followed by the interpretation rule. The enumerated codes are dense but each one earns its place by telling the agent what to report back to a user.

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 carries the burden of explaining the return value, and it does so adequately by listing the codes and stating that empty means sendable. The only real omission is any mention of the required input parameter or how to recover from a non-empty result.

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?

The description never mentions the single broadcast_id parameter, and schema description coverage is 0%. The parameter name is nearly self-explanatory and its type is unambiguous, so the gap is small, but the description does nothing to compensate for the undocumented schema.

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 ("List what would refuse scheduling or sending a broadcast now") and even enumerates the failure conditions it detects, which makes the tool's function unmistakable. It does not, however, distinguish itself from the sibling get_campaign_readiness, leaving the agent to infer that one is for broadcasts and the other for campaigns.

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?

Usage is implied rather than stated: the phrase "now" and "An empty list means it can send" signal this is a pre-flight check to run before scheduling. There is no explicit when-to-use guidance, no mention of running it after update_broadcast, and no reference to the campaign counterpart as an alternative.

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