look

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 describes the return format (numbered screenshot plus numbered element list) and implies a read-only observation, but omits permissions, side effects, and whether page state changes.

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?

A single sentence, front-loaded with the core output. Every word earns its place and there is no redundant or vague filler.

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?

Without an output schema or annotations, the description must explain return behavior. It names the two components (screenshot and element list) but leaves gaps: how the numbering maps to elements and what the screenshot contains are unspecified, which could matter for a tool used to drive subsequent actions.

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?

The tool has zero parameters, so no parameter semantics are needed. Per the rules, a zero-parameter tool receives a baseline of 4.

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 ('Show') and resources ('current page', 'numbered screenshot', 'list of the numbered elements'). It distinguishes itself from action siblings implicitly by being the observation tool, but does not explicitly name alternatives like browse or click.

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?

No when-to-use guidance, prerequisites, or alternatives are provided. The agent must infer that look is called before click/type to obtain element numbers, which is not stated.

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