take_snapshot

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does add useful context: timeout_ms failure behavior ('A hung error-page accessibility query returns an error without restarting the browser or replaying navigation') and explicit truncation limits. However, it does not state whether the tool is read-only or has side effects, though this is likely a read operation. The provided behavioral details are valuable but not exhaustive.

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. It front-loads the core purpose in the first sentence, then lists parameter explanations with clear formatting. No unnecessary words or redundancy. Each sentence contributes to understanding.

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 description covers the tool's purpose, parameter behavior, and error handling, which is sufficient for an agent to call it correctly. It lacks explicit read-only indication and guidance on when to use it, but these are minor gaps given the tool's simplicity and the absence of an output schema. Overall, it is fairly complete for a snapshot tool.

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 coverage is 0%, so the description must compensate. It does so well: timeout_ms is described as 'Maximum wait for snapshot collection' with a range, and max_nodes as 'Maximum retained tree containers' with depth and string truncation details. This adds meaning beyond the schema's simple types and defaults, giving the agent clear operational semantics.

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: 'Get a bounded accessibility tree, or a labelled DOM fallback.' This identifies the resource and distinguishes it from sibling tools like take_screenshot (visual capture) and get_page_info (page metadata). The term 'bounded' hints at constraints, but the exact nature is not elaborated here. It is specific and actionable, though not as sharply differentiated as the calibration example.

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?

There is no explicit guidance on when to use this tool versus alternatives. The phrase 'or a labelled DOM fallback' implies a fallback but does not explain conditions for choosing this over get_page_info, evaluate_js, or other DOM-related tools. No when-not-to-use or alternative selection criteria are provided.

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