look

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

Beyond the read-only annotation, it discloses important behavior: it does not bring the window forward, describes the numbered-element output, explains image attachment rules, and notes that an identical image is not reattached. However, it omits behavior around max_elements truncation, which matters for interpreting element lists.

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 purpose is front-loaded, but the remainder is a dense run-on block with semicolons, parentheses, and nested asides that make it hard to scan. Most information is relevant, but the structure sacrifices readability for compression.

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?

For a complex seven-parameter tool with no output schema, it explains the return format reasonably well and covers most modes. It still leaves gaps: max_elements behavior is unmentioned and detail semantics are only partially explained.

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 0%, so the description must carry parameter meaning; it does this well for show, marks, query, region, window, and partly detail. It completely omits max_elements, leaving one of the seven parameters with no semantic guidance beyond its default.

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 a specific verb and resource: 'See a window without bringing it to the front,' then specifies that it returns numbered elements and optionally an image. This distinguishes it from action-oriented siblings like act and from window enumeration tools like windows.

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 useful context such as 'omitted = current window' and explains when 'show=auto' includes an image, but it never explicitly names when to use look instead of act, windows, or window. The alternatives are only implied by the read-only inspection focus.

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