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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reinforces this with the meaningful detail 'opens nothing by itself', so the agent knows no state changes occur and a browser action must follow. It also characterizes the payload (step-by-step screens, buttons, fields), which matters since there is no output schema. It stops short of describing format length or failure modes when the account is missing.

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 critical fact (this returns instructions and creates nothing) is deferred behind a clause that reads like a create action, so the structure fights the purpose. The trailing note about Beautiful.ai's official API/connector, including a verification date, is tangential detail that adds length without changing tool selection, though the sentences themselves are not padded.

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 parameters and no output schema, everything the agent needs must come from the description, and it does cover what comes back and what to do next via cotlet_browser_*. What is thin is the preconditions: it never says what it needs (e.g., an authenticated Beautiful.ai session or account context) for the subsequent browser steps to succeed.

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 input schema has zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The description correctly implies no presentation content is supplied as arguments — the result is guidance, not a deck — which prevents an agent from hunting for missing inputs.

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 states a concrete behavior: it returns step-by-step instructions (screens, buttons, fields) for creating a presentation in the user's own Beautiful.ai account and 'opens nothing by itself'. That distinguishes it from the cotlet_browser_* action tools and from Beautiful.ai's official API/connector. However, the leading clause 'Create presentation in the user's own Beautiful.ai account' and the tool name both imply direct creation, so the true nature only becomes clear in the second half.

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 explicitly gives the follow-up path — once you have the steps, execute them with cotlet_browser_* in the user's Beautiful.ai Cloud Browser — which is actionable routing. It also names the official Beautiful.ai API/MCP connector as an existing alternative for outline-to-deck drafts, listing and export, though without an explicit rule for when to prefer one over the other.

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