Launch Browser

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

Annotations indicate openWorldHint=true and destructiveHint=false. The description adds that launch options can expose existing browser profiles, CDP sessions, or credential-bearing storage states, supplementing the annotations with useful behavioral context.

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 multiple sentences but front-loaded with the core purpose. Every sentence adds value, though it could be slightly more concise without losing clarity.

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 7 parameters (none required) and an output schema, the description covers when, preconditions, next steps, and sensitivity. It adequately prepares the agent, though it does not detail the output structure (handled externally).

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%, but the description mentions key parameters like profiles, storage state, and CDP endpoint. It also references the acknowledge booleans in preconditions. However, it does not explain each parameter in detail, limiting the added value for an agent.

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 states the tool launches a RawTrace-controlled Chromium session or opens a CDP endpoint/storage state. It distinguishes from siblings like browser_attach_cdp by specifying when a session is not running yet.

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?

Provides explicit when-to-use context, preconditions (authorization, acknowledgements), and next-step suggestions (navigate/inspect, then use browser_observe_action_result or monitor_start). Also implies when-not-to-use by mentioning 'not running yet'.

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