Attach to a localhost development tab to inspect and debug web apps; optionally authorize extra localhost origins without taking ownership of Chrome or tabs.
Attach to one selected localhost development tab. Optionally authorize exact additional localhost origins, such as a separate API port. Chrome and tabs remain user-owned.
| Name | Required | Description | Default |
|---|---|---|---|
| target_id | Yes | ||
| cdp_endpoint | Yes | ||
| allowed_origins | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It usefully discloses that Chrome and tabs 'remain user-owned' (non-destructive, no takeover) and that it 'attaches' rather than launches, but omits lifecycle (must be paired with browser_close_session), auth/permission needs, and failure conditions.
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?
Three tight sentences, front-loaded with the core action and followed by the optional behavior and ownership guarantee. No filler; only mild room to be more explicit about the target source.
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?
No output schema, no annotations, and 0% schema coverage for a 3-parameter tool. The description does not explain how to obtain target_id, what cdp_endpoint expects, or the session lifecycle, so an agent lacks enough to call it reliably.
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 0%, so the description must compensate. It conveys the intent of target_id ('one selected tab') and allowed_origins ('exact additional localhost origins'), but never mentions cdp_endpoint and omits the 8-origin cap, leaving the URI-format requirements undocumented.
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?
'Attach to one selected localhost development tab' gives a specific verb (attach) and resource (tab), and the session framing distinguishes it from sibling capture/network tools. It stops short of explicitly naming browser_list_targets as the source of the selected tab, but the scope is clear.
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 implied: you must already have selected a localhost tab, and the optional origin authorization is described as opt-in. There is no explicit when-to-use versus siblings (e.g., 'call browser_list_targets first') and no stated exclusions or preconditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.