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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description adds non-obvious context on top: it explicitly says it "opens nothing by itself" and returns step-by-step instructions rather than performing the change, which prevents an agent from assuming a mutation occurs. It does not describe output length, whether steps vary by plan type, or failure modes, which keeps it from a 5.

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 sentence (returns steps, then use browser tools) is front-loaded and valuable. But the opening "from ChatGPT, Claude or any AI agent" is filler, and the closing note about Recurly's REST API surface is tangential to invoking this specific tool and reads as justification rather than instruction.

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 describing the return value, and it does so concretely ("screens, buttons, fields"). For a simple, low-complexity guidance tool this is largely sufficient. It is slightly incomplete in not saying how the user's Recurly account/connection is established when no account parameter is supplied.

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—there is no parameter meaning the description needs to supply. The description does not attempt to invent or explain inputs, which is correct given the empty schema with additionalProperties=false.

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 uses a specific verb+resource ("Change subscription in the user's own Recurly account") and then explicitly reframes the actual behavior: it "Returns how to do it in Recurly step by step (screens, buttons, fields) and opens nothing by itself." That is clear enough to tell it is a guidance tool, not an executor. It stops short of 5 because it never contrasts itself with related siblings such as recurly_cancel_subscription or recurly_find_account.

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?

There is a usable workflow hint: read the returned steps, "then do it with the cotlet_browser_* tools in the user's Recurly Cloud Browser." That tells the agent what to do next, which is real guidance. However, there is no explicit when-to-use/when-not-to-use against the other recurly_* tools, and no stated preconditions (e.g., whether a Recurly connection must already exist).

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