browser_snapshot_frame

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

No annotations are provided, so the description carries the burden. It discloses key behavioral traits: it works for both same-origin and cross-origin frames, and returns the frame's ARIA tree with refs rewritten to 'fNeM' form for direct use. It does not mention any destructive behavior or rate limits, which is appropriate for a read operation.

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 with about 4 sentences. It front-loads the purpose and usage, then explains the parameter. There is no fluff, though it could be slightly tighter. Efficient overall.

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 complexity (3 parameters, output schema exists, sibling tools), the description covers the main parameter and usage scenario well. It does not explain session_id or depth, but these may be inferred from the context (e.g., session_id from browser session, depth for ARIA tree depth). With output schema present, return values are not needed. Mostly complete with minor gaps.

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 frame_ref well: 'a frame id ("f1"), an element ref inside the frame ("f1e36"), or the <iframe> element's own ref ("e81")'. However, it does not explain session_id or depth, leaving these parameters without added meaning. Partial compensation.

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 it snapshots a specific child frame and distinguishes from browser_snapshot by specifying when to use it (when iframe node has empty/collapsed children). The verb 'Snapshot' and resource 'child frame' are specific, and it differentiates from the sibling tool.

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 explicitly says when to use this tool: 'Use when browser_snapshot returns an iframe node with empty/collapsed children'. It also notes it works for same-origin and cross-origin frames, implying reliability. However, it does not explicitly state when not to use it, but the context is clear.

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