browser_snapshot

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

No annotations are provided, so the description must carry the behavioral burden. It does disclose the key behavior: outputs a numbered accessibility tree with [ref] prefixes. However, it omits other important behavioral details such as whether it changes the page state (it likely does not, but that's not stated), the size or format of the output (beyond the accessibility tree), and the fact that the refs are volatile across actions. The suggestion to 're-run after every action' implies, but does not explicitly state, that refs become stale, which is a critical behavioral trait.

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 short and front-loaded with the core purpose. The first sentence states the main function. The following sentences explain the [ref] convention and the recommendation to re-run, which are essential usage notes. It is efficient, though it could be slightly more explicit about behavior, but it earns a 4 for concise and purposeful structure.

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 output schema is present, so the description doesn't need to explain return values in detail. The description covers the core functionality, the ref system, and the guidance to re-run after actions. Missing are explicit details on output size limits (though max_nodes hints at it), staleness warning, and state safety. However, given the presence of the output schema and the tool's relatively simple nature, it is mostly 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 schema for max_nodes is fully described (10-400, default 240), so the description does not need to add meaning. Since schema_description_coverage is 100%, the baseline score is 3. The description adds no additional parameter context, but it is not required; the schema is sufficient.

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: reading the current page as a numbered accessibility tree. It specifies the resource (current page) and the format (accessibility tree), and explains the unique [ref] numbering system, which distinguishes it from siblings like browser_screenshot or browser_status.

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 instructs when to use the tool: after every action, to get the current state. It also explains how to use the output: pass a ref to other browser_* tools that accept a target. This provides clear both timing and integration guidance, exceeding the baseline.

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