start_session

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

With no annotations, the description carries the full burden. It discloses that the tool opens a browser, navigates to a URL, returns a snapshot with metrics, and provides a persona definition for roleplaying. It also mentions v0.3 device emulation support. This is transparent about the immediate effects and outputs, though it does not discuss side effects like session lifecycle or resource cleanup.

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 concise and well-organized. It opens with a clear action, lists return values, then gives the workflow and a version-specific note. Every sentence adds value without redundancy, and the structure is scannable.

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?

Given no output schema, the description sufficiently describes the return payload (first page snapshot, screenshot, Core Web Vitals, accessibility score, network summary) and outlines the overall workflow. It also provides version context for device emulation. It does not cover all edge cases or prerequisites, but for a session-start tool it is reasonably 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?

The input schema already provides 100% coverage for all five parameters, so the description adds little new semantic meaning. It does mention that device_profile supports device emulation and advises using list_devices, but this is more of a reference than an enrichment of parameter semantics. This aligns with the baseline of 3 for high schema coverage.

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's function: 'Start a user flow session. Opens a browser, navigates to the URL, and returns the first page snapshot...' This is a specific verb+resource with a defined scope. It also distinguishes itself from siblings by outlining the workflow 'start_session → step → end_session' and positioning this as the entry point.

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 gives explicit context for when to use this tool: it begins a session and then delegates future actions to the 'step' tool. The workflow line and the note about device_profile using list_devices provide practical usage guidance, though it does not explicitly list exclusions or alternative tools for simpler tasks.

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