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

Goes beyond the annotations by disclosing the return content (screens, buttons, fields) and the key behavioral fact that no action is performed — 'opens nothing by itself.' That is exactly the kind of context annotations cannot convey. Minor gap: no indication of length/format of the returned procedure.

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 instruction is front-loaded and clear, but the closing sentence about AppFlowy Cloud's REST API and 'no hosted MCP server (checked 25 Oct 2026)' is tangential justification, and 'from ChatGPT, Claude or any AI agent' is filler. Trimming those would sharpen the definition without losing information.

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 does the work of explaining what comes back, which is good. However, a restore operation with zero input parameters never explains how the target item is determined — presumably the user's own browsing session — leaving a real ambiguity about what the returned steps apply to.

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?

Zero parameters with a fully specified schema, so the baseline is 4. Nothing in the description is needed to explain parameters, and none is invented.

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?

Stays with a specific verb+resource ('restore from trash') but immediately reframes the actual behavior: it returns a step-by-step procedure rather than performing the restore. That reframing is valuable and distinguishes it from the action siblings, though the name-to-behavior mismatch costs a bit of clarity.

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?

Explicitly states the workflow: call this to get the steps, then execute them with the cotlet_browser_* tools in the user's AppFlowy Cloud Browser. It does not explicitly contrast with cotlet_app_guide, but the 'how to do it in AppFlowy' framing and the negative 'opens nothing by itself' make the division of labor clear.

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