open_urlOpens any link or file URL in its default app, such as a browser, Figma, Slack, or vscode://, with an option to capture the front window afterward to verify the result.
Open a link or file URL with its default app (browser, Figma, Slack deep links, vscode://, etc.).
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| look_after | No | Return a fresh screenshot of the front window after the action, to check the result |
Changes observed during successful MCP inspections.
v0.11.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations the description carries the full burden, and it does disclose the key behavioral trait: the URL is handed to the OS default app (browser, Figma, Slack, vscode://), so this escapes any built-in browser context. It says nothing about return values, whether it blocks/waits, or failure on unsupported schemes.
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?
One front-loaded sentence with zero filler; the verb+resource lead and the parenthetical examples earn their place by clarifying supported schemes.
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 simple two-parameter action tool with no output schema and no annotations, the description covers the core action but omits what the call returns, whether it waits for the app, and how failures surface — gaps the agent cannot fill from structured data.
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 coverage is 50%: look_after is documented inline, but the required url parameter is not. The description partially compensates by enumerating accepted URL forms (file URLs, app deep links, vscode://), which tells the agent what can be passed, but adds no format or validation detail.
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?
States a specific verb (open) and resource (link/file URL) plus the mechanism (default app handler) with concrete scheme examples. It is clear what the tool does, but it never contrasts itself with close siblings like browser_open, browser_navigate, or open_app, leaving the agent to infer the distinction.
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 no when-to-use or when-not-to-use guidance and no named alternative. The scheme examples hint at deep-link/OS-handoff scenarios, but the agent must infer that this is for external default-app opening rather than the in-page browser_* family.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.