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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description nonetheless adds real value by explaining that the tool only returns instructions, that execution is delegated to browser tools, and that ManyChat's official API is Pro-plan-only and narrow as of a dated check. That last point justifies why a guidance tool exists at all. It stops short of describing the shape/extent of the returned walkthrough or any cloud-browser session prerequisites.

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?

Core constraint (returns instructions only) is front-loaded in the second sentence, with the browser-tool handoff stated before the API caveat. The phrase 'from ChatGPT, Claude or any AI agent' is promotional filler that does not help tool selection and could be cut.

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 zero parameters, no output schema, and rich annotations, the description covers what an agent needs: what is returned, that nothing is executed, how to actually perform the action, and why the direct API is not used. Nothing material is left ambiguous.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; a baseline of 4 applies. The schema is closed (additionalProperties false) and empty, consistent with the described behavior.

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 second sentence states precisely what the tool produces: a step-by-step ManyChat walkthrough (screens, buttons, fields) and that it 'opens nothing by itself'. That resolves the misleading name 'send_broadcast' effectively. It does not, however, distinguish itself from the sibling manychat_send_inbox_message, which an agent could easily conflate with a broadcast.

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?

Explicit routing is given: this tool returns instructions, then execution happens via the cotlet_browser_* tools in the user's ManyChat Cloud Browser. The 'opens nothing by itself' clause is a clear when-not statement. What is missing is any exclusion relative to the other manychat_* siblings or guidance on when a direct-API path would be preferred.

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