restart_chrome

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

No annotations are provided, so the description carries the full behavioral burden, and it meets it thoroughly. It discloses that the operation is destructive — 'terminates that instance's Chrome process and all its open tabs; closes its debugging connection' — while reassuring that 'other instances keep running.' It also states the prerequisite (CHROME_PATH env var or chrome in PATH) and the return value. This is complete behavioral disclosure for a destructive mutation tool.

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 text is dense but every sentence earns its place: main action first, then side effects, prerequisites, return value, use cases, alternatives, and parameter notes. It is front-loaded with the core action and scoping constraint. Slightly long, but defensible given the tool's complexity (destructive restart with configurable presets, proxy, and multiple side effects to disclose).

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 destructive 3-parameter tool with no annotations and no output schema, nothing an agent needs is missing: purpose, side effects, prerequisite environment requirements, return format ('restart success confirmation listing the presets applied'), use cases, alternatives, and parameter constraints are all covered. Context is 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 coverage is 100% and the schema's own parameter descriptions are rich — they already explain the closed set for 'features', the proxy URL format, and the instance_id source. The description reinforces the closed-set constraint ('arbitrary Chrome flags are not accepted') and summarizes the presets, but adds only marginal meaning beyond what the schema already provides. The baseline of 3 is appropriate since the schema does the heavy lifting.

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 opens with a precise verb-plus-resource statement: 'Stops and restarts the Chrome instance selected by instance_id... with remote debugging enabled'. This clearly distinguishes it from sibling tools like 'reload' (refresh page), 'navigate' (load new content), and 'stop_chrome' (which only kills). An agent can identify what this tool does and what it is not without opening any schema.

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?

The description explicitly states when to use it: 'Use this to reset browser state, apply proxy settings, enable experimental browser capabilities, recover from crashes.' It also names alternatives with the conditions that select them: 'reload' to refresh without restart and 'navigate' to load new content. This is the full expected pattern — explicit when-to-use plus exclusionary routing.

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