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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the concrete return shape (step-by-step screens, buttons, fields) and that no browser action is triggered, which is exactly the kind of context an agent needs to avoid assuming side effects. It stops short of saying whether the guidance is version-dated or could go stale as Lichess UI changes.

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 behavioral core is front-loaded and clear, but the description carries filler: 'from ChatGPT, Claude or any AI agent' is promotional padding, and the closing sentence about Lichess's REST API and the absence of an official MCP server (with a date) is tangential trivia that does not help an agent select or invoke the tool. Two of the four sentences could be trimmed without losing operational meaning.

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 zero parameters, no output schema, and annotations covering safety and world scope, the description supplies what an agent still needs: the tool is a guidance generator, its output form is described, and the follow-up pathway through cotlet_browser_* is named. Nothing essential about invocation is missing, though a note on guidance freshness or what to do if Lichess UI differs would close the remaining gap.

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 additionalProperties=false, so there are no parameters whose meaning could be elaborated. Per the zero-parameter baseline this scores 4; the description does not need to explain any inputs.

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 states a specific outcome (exporting the user's own Lichess games) and then immediately clarifies the real behavior: it returns step-by-step instructions with screens, buttons and fields rather than performing the export. That correction is what lets an agent tell this apart from the cotlet_browser_* action tools it must use afterwards. The name modestly oversells ('export games') but the body resolves the ambiguity in the first sentence.

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 usage sequence: call this first for step-by-step guidance, then execute it with cotlet_browser_* tools inside the user's Lichess Cloud Browser, and it explicitly states the tool 'opens nothing by itself.' What is missing is any exclusion such as when to skip this and use the official REST API directly, even though the API is mentioned.

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