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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine behavior the annotations do not: the call performs no browser actions ('opens nothing by itself') and returns procedural instructions rather than data, preventing an agent from assuming a side effect occurred.

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 two clauses are front-loaded and useful, but the closing paragraph about Minuba's official API (41 resources, checked 31 Oct 2026) is tangential detail that dilutes the routing message. The sentence structure is also dense, packing the return behavior and the follow-up tool workflow into one run-on clause.

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 output schema, the description must convey what comes back; it says 'how to do it step by step (screens, buttons, fields)' but gives no sense of the response shape, length, or how steps are keyed to the browser tools. For a zero-parameter, read-only guide tool this is adequate but leaves the agent guessing about the returned artifact.

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 tool takes zero parameters, so the baseline is 4. The description correctly implies no inputs are needed and nothing additional is required to explain parameter meaning.

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 makes clear this is a how-to/recipe tool, not a data lister: it 'Returns how to do it in Minuba step by step (screens, buttons, fields) and opens nothing by itself'. That corrects the potentially misleading name 'list_orders', though the mismatch between name and actual behavior means the agent must read the description to learn it never returns order data.

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 routes the agent: read this guide first, then execute the steps with the cotlet_browser_* tools in the user's Minuba Cloud Browser. It also explains why the REST API is not an option (no self-serve key, no MCP server), which pre-empts a wrong path. It does not say when to prefer sibling tools like cotlet_app_guide or the other minuba_* tools.

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