browser_snapshot

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

Lacking annotations, the description carries the full transparency burden. It explains the output format (ref IDs) and the effect of the 'full' parameter, but does not mention side effects, rate limits, or if the operation is read-only. The behavior is mostly foreseeable given the 'snapshot' nature.

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-structured: a one-line purpose, a sentence about the output, and a bullet-like explanation of parameters. Every sentence adds value with no fluff.

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?

For a tool with two parameters and an output schema, the description covers the essential aspects. It could optionally mention error scenarios (e.g., invalid session_id) or the exact format of the returned snapshot, but it is sufficient for correct usage in most contexts.

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 has 0% description coverage, so the description fully compensates by explaining both parameters: session_id as the browser session ID and full with clear true/false behavior. This adds meaning beyond the bare 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 clearly states the tool retrieves a text snapshot of the accessibility tree, specifying the exact resource and verb. It distinguishes itself from sibling tools like browser_vision by focusing on text-based interaction and providing ref IDs for use with browser_click and browser_type.

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 that the output ref IDs are for use with browser_click and browser_type, giving a clear usage context. However, it does not explicitly compare with alternatives or state when not to use this tool, such as when a visual snapshot is needed.

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