mailkite_create_broadcast

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

The description claims the tool creates a broadcast draft, which is a write operation. Annotations have readOnlyHint=false, so there is no contradiction. However, the description does not disclose any behavioral traits beyond the action itself, such as whether it validates content, what happens on failure, or side effects. With readOnlyHint=false and no further context, the description adds little to the annotation. However, the bar is lower because readOnlyHint is already false, but the description should still add context; it mentions the return value and the requirement for a token, which is some value. So score 3 would be appropriate, but I need to justify: it does mention 'returns the broadcast with its id' and 'requires a management session token', which are behavioral details beyond the annotation. So score 3.

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 3 sentences, concise and structured logically: purpose, key parameter guidance, return and next step, and auth requirement. It is front-loaded with the main action. No fluff. Score 4 because it could be slightly more compact, but it's efficient.

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 tool with 10 parameters, no output schema, and no annotation beyond readOnly, the description is relatively complete: it covers required field, audience format, return value, and auth. However, it does not explain the meaning of other parameters (e.g., replyTo, footerAddress, templateId) or any validation rules. It also doesn't mention the 'filter' audience type that appears in the schema enum. This is a significant gap for a complex tool, so score 3.

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 0%, so the description must compensate. It clarifies that 'from' is required, and explains the 'audience' parameter with specific formats (type: 'all' or type: 'list' with id). It also mentions 'name', 'subject', 'html', etc. implicitly by listing parameters, but does not explain each. It partially compensates by giving examples for audience, but not for other parameters like templateId or footerAddress. This is a moderate compensation, so score 3.

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 that the tool creates a broadcast draft and returns its id. It distinguishes itself from siblings like mailkite_send_broadcast (which sends) and mailkite_update_broadcast (which modifies). However, it does not explicitly contrast with those siblings, but the action is clear.

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?

It indicates when to use it (to create a draft) and that sending is a separate step (sendBroadcast). It also gives a prerequisite: requires a management session token. It does not explicitly state when not to use it or mention alternatives, but the step-by-step guidance is helpful.

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