Bake Profile

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

No annotations are provided, so the description carries the full burden. It discloses blocking behavior (waits until user closes window), timeout with force termination, headful execution, and remote debugging bind requirements. It doesn't state whether existing profile state is overwritten or how persistent the bake is, but the mutating meaning is clear.

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?

Purpose is front-loaded, followed by workflow behavior, then a compact semicolon-separated parameter list. Every sentence conveys actionable information; no fluff or repetition. The SPEC.md reference is brief and doesn't bloat the description.

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 tool with 6 optional params, no annotations, and an output schema, the description covers the core workflow and most parameter semantics well. The main gape are that 'profile' is not explained and the behavior depends on an external SPEC.md section that may not be accessible to the agent.

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 0%, so the description must compensate. It adds meaningful semantics for method, start_url, cdp_host/cdp_port, and timeout_seconds, including defaults, ssh -X behavior, and the closed-network bind warning. However, the 'profile' parameter is not described at all, leaving part of the schema under-explained.

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?

Description states a concrete action: baking a new state (e.g. login) into a profile, and explains the interactive headful workflow. This clearly differentiates it from read-only siblings like search and fetch_page, and from import_profile, because it explicitly covers browser launch and waiting for user action.

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 method selection rules: auto based on $DISPLAY, display for direct display (including ssh -X), and cdp for display-less environments. It also gives timeout and start_url context. It doesn't explicitly state when to prefere bake_profile over import_profile or fetch_page, so it stops short of a full 5.

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