capture_flow

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

Without annotations, the description fully discloses key behaviors: state persistence across steps, API call reporting per step, pass/fail aggregation with screenshot on failure, and dev server requirement. This provides complete behavioral transparency for an AI agent.

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 a single focused paragraph with a strong front-loaded topic sentence. Every subsequent sentence adds essential detail (state, API calls, diagnostics, prerequisite) without redundancy or filler.

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 the tool's complexity (3 params, many action types, no output schema), the description covers flow building, navigation, interactions, error handling, and output expectations. It leaves no critical gaps for an AI agent to use the tool effectively.

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 100%, so baseline is 3. The description adds value beyond the schema by explaining interactive behavior (e.g., visible matches preferred, within scoping logic, per-step navigation vs actions). It enriches parameter understanding without repeating 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?

The description uses specific verbs ('Drive', 'screenshot') and clearly identifies the resource ('multi-step user flow against a SINGLE persistent page'). It distinguishes from siblings by highlighting the multi-step, stateful nature, which is unique among sibling tools like check_page or inspect_rendered_page.

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 explains when to use this tool (for multi-step flows with navigation and interactions) and implicitly contrasts with simpler siblings. It notes a prerequisite ('Requires the dev server to be running') but lacks explicit when-not-to-use guidance or alternatives.

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