browser_ensure

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

The description goes beyond annotations by specifying viewport defaults (1280x720), the requirement for lease_id, non-durability across MCP process death, and loopback isolation. Since annotations are all false and provide no hint, these details add significant operational context without contradiction.

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 three sentences long, front-loading the primary purpose, then adding essential parameter defaults and caveats. Every sentence contributes value, with no redundant phrasing.

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?

Core behavior and caveats are covered, but the description does not explain the origin/role of lease_id (presumably workspace_acquire) or the semantics of force. Given the low schema coverage and the presence of an output schema, these omissions leave the description only moderately complete.

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 explains width and height with defaults, and notes lease_id as required, but entirely omits the force parameter. This is a notable gap given the absence of schema descriptions.

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 clearly states the tool starts or reuses an isolated headless Chromium session with loopback browsing. It distinguishes from visual_capture but does not explicitly contrast with browser_open, which could cause slight ambiguity. The core purpose is still unambiguous.

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 mentions that screenshots belong to visual_capture and that the session is not durable unlike tmux, providing some exclusions. However, it does not explicitly state when to use this tool versus browser_open or other browser siblings, nor that it should be called before using browser actions.

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