session_open

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

With no annotations, the description carries the full behavioral disclosure burden; it successfully does so by stating that the session is recorded as video, trace, screenshots, and logs until session_close. It also discloses that the session is interactive and that this call returns both navigation results and a screenshot. It doesn't mention auth requirements or cleanup costs directly, but the lifecycle is adequately surfaced.

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 with no filler: it front-loads the action and return values, then gives the essential lifecycle fact and the sibling-tool pointer. Every sentence earns its place.

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?

The description adequately covers the core flow: open, get id/navigation/screenshot, record until close, and use session_act for interactions. However, given the complexity of the options object and the absence of an output schema, an agent may still lack enough context about optional behaviors like headless mode, browser choice, and timeout semantics. It is usable for basic calls but not fully complete for advanced usage.

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?

The schema has near-zero description coverage for the parameters, and the description compensates only minimally by mentioning 'a URL.' The large 'options' object with many settings (headless, browser, mode, timeouts, etc.) is left entirely unexplained, so an agent has to infer or remember what those mean. This is below the minimum viable level given the schema's lack of help.

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 uses a specific verb ('Open'), names the resource ('browser session on a URL'), and states the concrete return values: id, first navigation result, and screenshot. It also distinguishes itself from siblings like session_act and session_close, so an agent can tell this tool apart without opening the 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?

The description clearly implies when to use this tool: to start an interactive recorded session. It provides guidance for the next step by saying 'Use session_act to drive the page step by step,' which is a clear context cue. However, it does not explicitly state when not to use this tool versus alternatives, so it stops short of a 5.

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