Directly run ONE browser tool (bypass the worker)

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

With no annotations, the description covers key behaviors: return envelope format (ok/data/error), browser-side dispatch never throws, validation of unknown tools and missing params, concurrency constraints, token cost, and browser version requirement. Lacks explicit statement of read/write nature or idempotency.

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?

Single paragraph with front-loaded purpose, uses symbols (★, ⚠) for emphasis. Every sentence adds distinct value. Could be slightly more structured with bullet points, but current format is efficient and scannable.

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 3 parameters, 1 required, no output schema, and nested objects, the description adequately covers prerequisites, return format, concurrency rules, and requirements. It does not exhaustively list all error scenarios but delegates tool-specific details to agent_tools.

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%, so schema already documents parameters. Description adds context by advising to consult agent_tools for parameter details and gives examples of tool names. It clarifies workspaceRoot's effect on file operations. Overall, description adds marginal value beyond schema.

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 that this tool directly runs a browser engine tool, bypassing the DeepSeek worker, and contrasts it with delegating to the worker. It explicitly identifies the director agent as the user and distinguishes from sibling tools like agent_send by highlighting performance and cost tradeoffs.

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 guidance: use when direct, fast execution is needed; explains token cost implications; instructs to check agent_tools first for name and parameters; warns about concurrency conflicts with active agent sessions and provides steps to resolve (agent_stop/agent_wait_for_stop).

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