CDP: Launch

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description adds the concrete consequence the annotations don't convey: force_restart CLOSES the running window and reopens with the logged-in profile. It does not mention port conflicts, failure modes, or what launch returns, but for an annotated mutation tool this is solid added context.

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 sentences, zero filler, and the core purpose is front-loaded before the app list and the destructive warning. The parenthetical about closing the window earns its length because it is the highest-risk detail.

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 launch tool with no output schema and annotations covering the destructive flag, the description supplies the app domain and the dangerous side effect. It omits any pointer to companion tools (cdp_launched/cdp_stop) or cleanup expectations, but nothing needed to invoke it correctly 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 the baseline is 3, but the description adds meaning the schema does not: it supplies the enumerated app values (schema has no enum) and explains the real-world effect of force_restart (window closed, profile reopened) beyond the schema's terse '(destructive)'. The remaining params (port, headless, user_data_dir, load_extension) are left entirely to the 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?

States a specific verb (Launch) and resource (an app with a CDP debug port) plus the reason it exists ('so it can be driven'). It also enumerates the valid app ids (chrome|edge|brave|discord|notion|slack|vscode) or an executable path, which the schema lacks as an enum, so an agent can pick it apart from siblings like desktop_app or cdp_new without opening a 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?

It gives clear context for use (launching an app so CDP can drive it) and a specific conditional rule: Electron apps (discord/notion) need force_restart when already running. It does not name alternatives such as cdp_launched to check state or cdp_stop to clean up, so it stops short of full when/when-not guidance.

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