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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description reinforces this with the important disclosure that the tool 'opens nothing by itself' — resolving the apparent mismatch between the create-sounding name and a read-only profile. It adds real context (output is procedural, an external browser step is required) but says nothing about prerequisites such as account or Cloud Browser availability, or what the returned steps look like.

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?

Three sentences, front-loaded with the action, followed by the operational caveat and the follow-up tooling. The trailing 'Midjourney's official API: Midjourney has no public API (checked 5 Nov 2026)' is awkwardly phrased and marginally useful as rationale, but most of the text earns its place.

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, the description carries the burden of explaining returns, and it does so at a high level ('step by step: screens, buttons, fields'), plus the required follow-up tooling. It is nearly complete for this tool's complexity; the missing piece is any precondition note about the user's Midjourney account or Cloud Browser session.

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?

There are zero parameters, so the baseline is 4, but the description supplies no input-shape information whatsoever — notably, it never explains that the caller passes no arguments (prompt, style, aspect ratio) and that this information must instead be conveyed during the browser step. That omission is a small but real semantic gap.

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 uses a specific verb and resource ('Create images in the user's own Midjourney account') and immediately clarifies the non-obvious mechanic: it returns step-by-step instructions rather than performing creation itself. It is meaningfully distinct from upscale/vary/animate siblings, though it does not explicitly contrast with them by name.

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 gives clear sequencing guidance: call this first, then execute the steps with the named 'cotlet_browser_*' tools in the user's Midjourney Cloud Browser. It stops short of stating when NOT to use it (e.g., when a creation already exists and you want to upscale or vary it), leaving that inference to the agent.

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