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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by explaining the mechanism ('drawn by a real browser'), which signals a rendering round-trip rather than a cheap metadata read, and by naming the two viewport widths. It stops short of saying what form the picture comes back in (URL, attachment, inline data), which matters given there is no output schema.

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?

Dense but front-loaded: the first clause tells the agent exactly what comes back, then the contents, then the usage condition and the parameter notes. A couple of clauses are padded (the parenthetical about readCampaign repeats the usage point), but nothing is genuinely wasted.

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 four parameters, full schema coverage and no output schema, the description covers purpose, mechanism, device scope and the variant flag well enough to call the tool confidently. The one real gap is the shape of the returned image, which an agent must know to use the result; that is the only thing keeping it from a 5.

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 100% and both enum parameters are documented in the schema itself, so the schema does the heavy lifting. The description's 'computer's width or a phone's' and "'b' shows version B of a test of two emails" largely restate the schema descriptions rather than extending them, and workspaceId is not discussed at all. Baseline 3 is appropriate.

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?

States a concrete verb and resource (render a campaign as a picture at desktop or phone width) and enumerates what the image contains: layout, products, pictures, button. It also explicitly contrasts itself with readCampaign, which returns blocks as data rather than appearance, so an agent can pick between the two without opening a schema.

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?

Gives a clear, actionable context: use it to check a campaign you drafted or changed before telling someone it is ready, or to describe it. The alternative (readCampaign) is named with the reason to prefer it for structural data. However, other plausible alternatives in this large sibling set (previewCampaign, previewSend, sendTestCampaign) are not addressed, so the routing is not exhaustive.

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