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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description is consistent with them, explicitly saying it 'opens nothing by itself.' It adds real context beyond the annotations: it describes the return content (screens, buttons, fields) and the required follow-up browser tooling. It does not cover prerequisites such as whether a Cloud Browser session must already exist, which keeps it at 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 clarification ('opens nothing by itself') and the follow-up tool family are front-loaded and easy to act on. The parenthetical about the official API/MCP server with a checked-on date preempts a plausible wrong path, though it is slightly digressive. No sentence is pure filler, but the ChatGPT/Claude enumeration is decorative.

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 what comes back, and it does: step-by-step screens, buttons, and fields. It also explains how the result is meant to be consumed, which is the key missing piece an agent would otherwise have to guess. Minor gaps remain around session prerequisites and whether the returned steps are account-specific.

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 is an empty object with no properties, so there are no parameters whose meaning needs explaining. The description adds the relevant scoping fact that the action targets the user's own Postscript account. Baseline of 4 applies for a zero-parameter 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?

States a specific verb and resource ('Create keyword in the user's own Postscript account') and immediately clarifies the actual mechanism: it returns step-by-step UI instructions rather than performing the creation. It also names the follow-up tool family (cotlet_browser_*), which separates it from the other postscript_* siblings. The residual weakness is that a reader must get past the 'Create' framing to understand this is a guidance tool.

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 workflow: call this to get the steps, then execute them with cotlet_browser_* in the Postscript Cloud Browser. The note that Postscript's official API and MCP server do not build or send campaigns usefully steers the agent away from a dead end. It stops short of explicitly stating when NOT to use this (e.g. vs. a native API-backed sibling), so it is not a full 5.

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