cb_launch

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

Goes well beyond the annotations by disclosing the single-instance lock, endpoint reuse behavior, that killing discards unsaved work, and the unsandboxed-shell constraint. The only minor gap is not describing what the tool returns on success (e.g. endpoint URL) — a 4 rather than 5.

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?

Three tight sentences plus a NOTE, front-loading the core action before the failure mode, the destructive caveat, and the environment constraint. Every sentence carries distinct operational value.

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?

With annotations carrying the destructive/idempotency profile and the schema documenting both params, the description still supplies the crucial environmental prerequisite (unsandboxed shell) and consent requirement. Nothing an agent needs to invoke it safely 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 coverage is 100%, so both parameters are already documented, including the default timeout and the destructive nature of kill_existing. The description reinforces the kill_existing consent requirement but adds no syntax or extra meaning beyond the schema, matching the baseline 3.

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 (launch) and resource (CyberBrick desktop app) plus the distinguishing detail that it starts with the CDP debug port on 9223. This is clearly separable from siblings like window_list, cb_health, or project_open_editor.

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?

Explicit about conditions: reuses a reachable CDP endpoint, fails if the app runs without the debug port unless kill_existing=true, and must run from an unsandboxed shell. It also names the required user-consent precondition before killing, leaving nothing to inference.

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