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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, and the description is consistent with them ('opens nothing by itself'). Beyond that it discloses the shape of the return value (step-by-step screens/buttons/fields) and the rationale that Judge.me has no official MCP server, which explains why the browser path is required. It does not mention whether the steps are version-specific or how to verify success.

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 front-loaded correction about not opening anything is the most useful sentence and appears early, but the phrasing is clumsy and repetitive ('Hide review in the user's own Judge.me account from ChatGPT, Claude or any AI agent'). The closing sentence about the REST API, private token, OpenAPI file and the 'checked 23 Oct 2026' date is background rationale that only partly earns its place.

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 so at a useful level of detail. It also points to the follow-up tools needed to complete the task. The remaining gap is that it does not say how the returned steps should be adapted if the Judge.me UI differs.

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 has zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. It correctly implies no inputs are needed because the tool only returns instructions.

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 corrects an ambiguity in the name by stating the tool 'Returns how to do it in Judge.me step by step (screens, buttons, fields) and opens nothing by itself' – so the agent learns this is a guidance tool, not an action tool. It is clearly separable from the cotlet_browser_* siblings it hands off to. The opening clause ('Hide review in the user's own Judge.me account from ChatGPT, Claude or any AI agent') is a bit garbled and reads like an action statement before the correction lands.

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 sequence: call this to get the steps, then 'do it with the cotlet_browser_* tools in the user's Judge.me Cloud Browser.' That is a concrete when-to-use signal and names the alternative. It stops short of saying when not to use it (e.g. when the agent already knows the flow), 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.