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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent with that profile. Beyond the annotations it adds genuinely useful context: the tool "opens nothing by itself," it returns screen/button/field-level steps, and Redbubble has no seller API or official MCP server (with a checked date). What it omits is whether the returned instructions vary by account state or whether they can be cached/reused across sessions.

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, each doing distinct work: identity, actual behavior plus handoff, and the external-API caveat. The API note is slightly tangential to invoking this tool, and leading with a verb ("List") that mispredicts the return value weakens the front-loading. No filler or repetition otherwise.

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?

There is no output schema, so the description must explain the return value, and it does so concretely (step-by-step screens, buttons, fields). Combined with the browser handoff and the no-official-API note, an agent has enough to call it correctly. It would be stronger if it stated what happens when the user is not logged in or when the instruction set is stale.

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 (additionalProperties: false), so there is no parameter meaning for the description to carry; baseline 4 applies. The description does not waste words inventing parameters that do not exist.

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 first sentence claims the tool will "List designs in the user's own Redbubble account," but the second clarifies that it actually "Returns how to do it in Redbubble step by step" and "opens nothing by itself." That is a real mismatch between the stated action and the delivered payload, so an agent cannot be certain whether it receives design data or instructions until it reads to the end. It does distinguish itself from the cotlet_browser_* tools by naming them as the executor, which keeps this above a pure tautology.

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?

The description gives a usable sequence: call this first, then perform the work with the cotlet_browser_* tools in the Redbubble Cloud Browser. It does not say when to prefer this over sibling tools such as redbubble_get_analytics or when to skip it because the browser session is already open and authenticated. Usage is implied through the two-step flow rather than stated as explicit include/exclude criteria.

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