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 carries the full burden and delivers: it discloses the return envelope (ok/data/error), that browser-side dispatch never throws, that unknown tools and missing params are validated, the token-cost side effect, the worker-session conflict rejection, and a minimum browser version. This is unusually rich behavioral context for a mutation-capable dispatch tool.

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 ★ marker and core purpose, then cost, prerequisites, and conflict handling in priority order. It is dense and clause-heavy, but every sentence carries distinct operational information rather than filler.

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 complex dispatch tool with no output schema, the description covers usage conditions, cost, conflict handling, prerequisites, and a rough return envelope. It stops short of detailing error shapes or what happens on partial failure, but nothing critical for correct invocation is missing.

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 100%, so the schema already documents name, args, and workspaceRoot. The description only adds a pointer that name/params come from agent_tools, which is mildly useful but does not extend the parameter semantics beyond the schema. 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?

States a precise verb+resource: personally run ONE browser engine tool while bypassing the DeepSeek worker. It explicitly contrasts itself with the delegation path (agent_start/agent_send), so an agent can distinguish it from siblings like agent_send without opening schemas.

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?

Gives explicit when-to-use (strong model drives engine-level tools faster/more accurately), when-not (each round burns director tokens, breaking the cost split; use the agent_start/agent_send flow if not needed), and prerequisites (query agent_tools first; stop/wait for a running worker session). Alternatives and exclusion conditions are all named.

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