launch

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

Annotations indicate non-readonly, non-destructive, idempotent, and open-world. The description adds behavioral details: uses normal profile, auto-detects if no browser/path provided, and closes a running instance without Marionette. This context aids understanding of side effects beyond what annotations provide.

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 description is concise—four sentences—with essential information front-loaded: the primary action and purpose. Every sentence adds value: specifying supported browsers, input options, auto-detection, and handling of running browsers.

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?

Given the lack of an output schema, the description adequately covers the tool's core behavior: launching a browser with Marionette, input methods, and handling existing instances. It could mention what happens after launch (e.g., returns a connection handle), but completeness is strong for a relatively simple tool.

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?

Both parameters ('browser' and 'path') have descriptions in the input schema, so schema coverage is 100%. The description reinforces that 'path' overrides 'browser' and mentions auto-detection, adding minor value. With full schema coverage, baseline 3 is appropriate.

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 clearly specifies the tool launches a Firefox-based browser with Marionette enabled, using its normal profile. It explicitly names the supported browsers (Firefox, LibreWolf, Waterfox, Zen, Mullvad) and distinguishes from the sibling tool 'launch_floorp' by stating 'Use for non-Floorp browsers.'

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 explains when to use the tool (for non-Floorp browsers) and how to specify the browser via 'browser' name or 'path' executable, with auto-detection fallback. It also advises to close an already-running instance without Marionette first. However, it does not explicitly exclude other use cases or provide alternatives beyond the sibling.

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