dify_browser_launch

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

With no annotations supplied, the description carries the full burden and does disclose meaningful behavior: an isolated profile that does not touch the everyday browser, a debug port, and the key auth prerequisite of a one-time manual login before reuse. It stops short of stating whether the call blocks until the page loads, what is returned (port, endpoint), or what happens if the port is already occupied.

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?

Two compact sentences, front-loading what the tool creates and why it is isolated, then the login-then-reuse caveat. Nothing is padded, though '带调试端口并打开 Dify' slightly repeats the port hint already given by the schema.

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?

For a launch tool with no annotations and no output schema, the essential intent and the login prerequisite are covered, but the agent is left guessing about return value, blocking behavior, idempotency when a session exists, and how this relates to dify_browser_status. Adequate, not complete.

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?

Schema description coverage is 100% and both parameters are documented in the schema, so the baseline is 3. The description only alludes to the debug port without stating a default and says '打开 Dify' without explaining how alias selects the target site, so it adds little beyond the structured fields.

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: launching a dedicated Chrome window with an isolated profile directory, a debug port, targeting Dify. The parenthetical '独立配置目录，不动日常浏览器' clarifies scope and distinguishes it from opening the user's normal browser, though it never names a sibling such as dify_browser_status to contrast with.

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?

Usage is only implied: one infers this must be called before browser-dependent operations, and the note that first-time login is required then later reused gives lifecycle context. There is no explicit when-not-to-use guidance, no mention of what to do if a window is already running, and no pointer to dify_browser_status for checking state.

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