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 is consistent with them ('opens nothing by itself'), avoiding any contradiction. It adds genuinely useful context beyond the annotations: the return value is a step-by-step screen/button/field guide, and follow-up action must go through cotlet_browser_* tools. A minor gap is that it does not say how large or structured that returned guide is.

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 core mechanic is front-loaded in the first two sentences, but the phrase 'from ChatGPT, Claude or any AI agent' is filler and the final sentence about Postscript's official API, including a dated parenthetical '(checked 23 Oct 2026)', reads as defensive justification that could be compressed to one clause. The content is useful but not tightly edited.

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?

For a zero-parameter, no-output-schema tool with an explicit read-only annotation set, the description covers what matters: it explains what is returned (a step-by-step guide), that no action occurs, and which tools must execute the plan. The one thing an agent might still want—whether a browser session must already be open before the follow-up—is implied but not stated.

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 and the schema is trivially complete, so the baseline is 4. The description correctly gives no parameter details and instead spends its space on return behavior and next steps, which is the right allocation for a no-argument tool.

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 names a specific resource (a Postscript campaign draft) and clarifies the key twist that the tool returns step-by-step instructions rather than creating anything: 'Returns how to do it in Postscript step by step (screens, buttons, fields) and opens nothing by itself.' It also distinguishes itself from the cotlet_browser_* execution tools and from Postscript's official API/MCP server. The only residual ambiguity is that the tool name 'create_campaign_draft' implies a write while the actual output is guidance, which the description has to correct rather than the name supporting it.

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 states the workflow: use this tool to get the instructions, 'then do it with the cotlet_browser_* tools in the user's Postscript Cloud Browser,' and that it 'opens nothing by itself.' That is clear context plus a named alternative. It stops short of explicitly excluding the API-based sibling operations (e.g., why not use postscript_schedule_campaign), so it is not a full when/when-not routing statement.

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