ui_snapshot

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

With no annotations, the description carries the behavioral burden and does substantial work: it explains that output includes refs and box coordinates, that selector scopes to a subtree, how frame routing works, and that VTable canvas cells are excluded. The only notable omission is the behavior/effect of the depth parameter.

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 front-loaded with the core purpose and then uses compact, well-separated paragraphs for VTable caveat, selector behavior, and frame modes. Every sentence adds useful information with no filler or restatement of the schema.

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?

Overall it equips an agent to call the tool correctly in most cases: purpose, output nature, frame semantics, selector scoping, and the canvas limitation are all covered, and an output schema exists. It falls short only on depth and lacks an explicit pointer to sibling vtable tools for canvas-cell access.

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 adds real semantics for boxes and ai_mode (mode='ai' + boxes), selector (subtree scoping), and frame (None/active/vtable/name-or-URL rules). However, depth receives no explanation, leaving one of five parameters under-specified.

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 opens with '抓取页面 aria 快照(mode='ai' + boxes)' — a specific verb, resource, and mode — and frames the output as a '语义之眼' accessibility tree containing refs and viewport boxes. This clearly distinguishes ui_snapshot from screenshot/overlay siblings by presenting it as an a11y-tree reader.

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?

It gives an explicit when-to-use cue: '交互前先读快照,再决定点哪个' (read snapshot before interacting), and explains that VTable canvas cells are absent from the a11y tree and instead use deterministic geometry. It doesn't explicitly name the alternative vtable_* tools, so it stops short of an explicit routing statement.

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