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

Given readOnlyHint=true and destructiveHint=false, the key risk is an agent assuming the campaign was actually stopped; the description closes that gap explicitly with 'opens nothing by itself'. It adds the return shape (step-by-step screens, buttons, fields) and the required downstream browser workflow, which annotations cannot convey. It stops short of covering failure modes (e.g., campaign already paused, or what to do if the browser session is not open), keeping it at a 4.

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 caveat ('opens nothing by itself') is front-loaded in the same sentence as the return description, and the follow-up instruction comes before the API aside. The API sentence is slightly awkwardly phrased and repeats the word 'Postscript', and the dated parenthetical 'checked 23 Oct 2026' is heavy for the value it adds, but overall there is little waste.

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 this covers everything essential: what it returns, that it has no side effects, and which tools execute the change. The one open question an agent might still have is how the guidance text is scoped to a specific campaign when there are no arguments, which the description leaves implicit.

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?

With zero parameters and 100% schema coverage there is nothing to disambiguate, so the baseline of 4 applies. The description correctly implies no inputs are needed because the action target is resolved through the user's own account context.

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 verb and resource ('Stop campaign') scoped to 'the user's own Postscript account', and immediately corrects the misleading name by stating it 'Returns how to do it in Postscript step by step' rather than performing the action. It is clearly distinguishable from siblings like postscript_schedule_campaign or postscript_create_campaign_draft because it is the guidance-only variant. The only blemish is that the opening sentence reads like an action until the second sentence reframes 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 gives an explicit follow-up path: call this to get steps, 'then do it with the cotlet_browser_* tools in the user's Postscript Cloud Browser'. It also preempts the obvious alternative ('Postscript has an API and an official MCP server, but neither builds or sends campaigns'). It does not state conditions for not using it, but the when-to-use signal is strong and unambiguous.

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