snapshot

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

Beyond the readOnlyHint annotation, the description discloses genuinely non-obvious behavior: shadow DOM traversal, that repeated items (grids, lists) are collapsed after a few, and that refs go stale after screen changes. The staleness warning is the kind of operational caveat an agent cannot infer from the schema and would otherwise get wrong.

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?

Three tight sentences, front-loaded with what the tool returns, then the ref contract, then the staleness caveat. Every clause carries information an agent needs; nothing is restated from the schema or annotations.

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?

With no output schema, the description still conveys the shape of results (elements with refs, optional selectors via schema) and the safety profile is covered by readOnlyHint. Minor gap: it doesn't say what an element entry looks like beyond the ref, or how truncation is signaled in the response.

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%, so `max`, `within`, `collapse`, and `selectors` are already documented in the schema. The description only reinforces the collapse concept ('repeated items collapse after a few') and does not explain `within`, `selectors`, or the interaction between `max` and `collapse`. Baseline 3 is appropriate.

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?

States a specific verb and resource (lists visible interactive elements) with concrete examples (buttons, tabs, inputs, cards, nav items) and a distinguishing technical detail (pierces shadow DOM). It also names the return contract — each item carries a ref usable by click/hover/type/query — which separates it cleanly from those sibling action tools.

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?

Gives an explicit lifecycle rule: 'Take a new snapshot after the screen changes: refs go stale,' which tells the agent when to re-invoke rather than reuse stale refs. It also implicitly routes to click/hover/type/query as the consumers of its output. No explicit when-not-to-use or named alternative (e.g. vs. `state`) is stated.

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