Directly run ONE browser tool (bypass the worker)

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

With no annotations supplied, the description carries the full burden and does so well. It discloses token cost, the ok/data/error envelope, never-throw dispatch behavior, validation of unknown tools/missing args, concurrency rejection, and the minimum browser version.

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 dense but well-organized: purpose, cost tradeoff, prerequisites, return envelope, and concurrency warning each earn their place. The warning is clearly marked and front-loaded enough to prevent misuse.

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?

Despite having no output schema, the description covers invocation semantics, error model, concurrency constraints, version requirements, and discovery flow. This is complete for a generic direct-dispatch tool with three parameters.

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 the baseline is 3. The description adds value by telling the agent to populate args per agent_tools params and clarifying that workspaceRoot affects fs_*/run_node/trace persistence, which reinforces the schema rather than merely repeating it.

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 states a specific action: directly run one browser engine tool, bypassing the DeepSeek worker. It clearly distinguishes this from delegation-based sibling tools like agent_start and agent_send, so an agent can select it correctly.

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 tells the agent to look up names/params via agent_tools first, to prefer agent_start/agent_send for cost-saving flows, and to stop any running agent session before direct calls. This is strong when-to-use and when-not-to-use guidance.

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