browser_snapshot

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the tool is a snapshot (non-mutating) and returns accessibility tree data, but it does not describe output format, whether it requires a valid session, or any potential waiting/loading behavior. This is partial but has clear gaps.

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, well-structured sentence that is front-loaded and contains no unnecessary words. It earns its place fully.

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 tool is simple (one optional param), but without annotations or an output schema, the description needs to cover behavior and usage. It clearly states the outcome (accessibility tree snapshot) but lacks explicit usage guidance, output format, or behavioral details like session requirements. Adequate but with notable 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 100% for the single parameter (sessionId), so the schema already documents it. The tool description adds no additional parameter context beyond what the schema provides, hence the baseline score of 3.

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 a specific verb ('Get') and a clear resource ('accessibility tree snapshot of the page'), with a stated purpose ('for AI-friendly element references'). It effectively distinguishes this from sibling tools like screenshot (visual), get_html (raw HTML), and get_text (text).

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 phrase 'for AI-friendly element references' implies a clear usage context: use when you need a semantic, AI-accessible representation of page elements. However, it does not explicitly name alternatives or state when not to use it, so it falls short of the top score.

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