browser_start

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

With no annotations, the description carries the full burden and does well: it discloses per-agent isolation, that a state-bound browser is restricted to that state's allowed origins, and that a browser surviving a reconnect is re-adopted with its tabs. It doesn't cover failure modes or what happens if a browser is already running with conflicting settings, leaving a small gap.

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?

Front-loaded with the core action and the optionality caveat, then the explicit reasons to call it. Dense but every sentence carries information; the reconnect sentence is slightly tangential but useful.

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 six-parameter, all-optional tool with no output schema and no annotations, the description covers identity, isolation, origin restrictions, and reconnect behavior well enough to call it correctly. Return-shape details and behavior on a second call are the only notable omissions.

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 already 83%, but the description adds real meaning: it groups the tuning parameters (headless/viewport/channel), explains the state parameter's origin-restriction consequence, and cross-references state_list. It still doesn't clarify the distinction/additivity of allowedOrigins versus a state's own allowed origins.

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+resource ('Start this session's own Chrome') and immediately scopes it as isolated from every other agent, which cleanly separates it from siblings like browser_status, browser_restart and browser_stop. An agent can identify the tool's action and its unique session-scoped nature without opening the 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?

Explicitly says the call is optional because the first browser tool call starts one with defaults, then names the exact reasons to invoke it eagerly: load a saved login state, choose headless/viewport/channel, or open a URL. This is genuine when-to-use/when-not-to-use guidance with conditions.

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