AI snapshot

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

Annotations already declare readOnlyHint=true, so the description's addition of 'accessibility snapshot' and the mention of reusable refs adds some behavioral context beyond the safety profile. However, it doesn't specify what the snapshot contains (e.g., full accessibility tree, only visible elements), the return format, or any side effects like state changes. It adds moderate value but leaves 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 just two sentences, both front-loaded with the core purpose. The first sentence states what the tool returns, and the second provides a concrete usage example. There is no redundancy or filler, making it efficient for an agent to parse quickly.

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 (9 parameters, 15 siblings, no output schema), the description adequately identifies the tool's output but does not explain workflow ordering (e.g., prerequisite of having a page loaded) or the full structure of the return value. The mention of refs and getByRef partially compensates, but the lack of output schema makes the description insufficient for complete understanding of what the agent receives.

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% – all 9 parameters are individually described in the input schema. The tool description adds no parameter-specific information, so it neither enhances nor detracts from what the schema already provides. A baseline score of 3 is appropriate per guidance.

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 returns an 'AI-friendly accessibility snapshot', which identifies the verb ('Return') and resource ('accessibility snapshot'). This distinguishes it from the sibling 'screenshot' (visual) and 'evaluate' (JavaScript) tools, though it doesn't explicitly name those alternatives. The wording is specific enough to convey the tool's basic purpose.

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 provides a usage hint ('Use refs like e12 with getByRef in a later run, or pass snapshotRef to click/fill/type'), which implies the snapshot is used for subsequent interaction. However, it offers no explicit comparison to siblings (e.g., when to use snapshot vs. evaluate or screenshot) and no prerequisites or when-not-to-use guidance. The usage context is implied but not fully directed.

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