box_of

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

No annotations are provided, so the description carries the full burden. The return shape {x, y, w, h, visible, tag, text} is helpful, but the description doesn't disclose behaviors like whether it matches one or many elements, what happens on no match, whether it's read-only, or whether scrolling affects coordinates. The visible field hints at visibility info but nothing is explained.

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 a single concise code-like line with zero wasted words, which is efficient. However, it's under-specified rather than truly concise — it communicates a return signature but fails to explain tool purpose and parameters. Efficiency without content doesn't earn a high score.

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 tool with 2 parameters (1 required), 0% schema coverage, no annotations, and no output schema, the description is severely inadequate. A single code-style return signature with an unexplained tab parameter and no behavioral notes leaves an agent guessing about invocation behavior, edge cases, and return semantics.

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 compensate for the undocumented parameters sel and tab. The example shows sel is a CSS selector string (via '".btn"'), which adds minimal value. The tab parameter is entirely unexplained — its type, default, and purpose are unclear, and the description adds nothing about it.

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 is a code example showing 'box_of(".btn") → {x, y, w, h, visible, tag, text}' rather than a prose statement of what the tool does. It implies the tool returns geometry/visibility data for a CSS selector match, but the purpose is only implied, not stated. It doesn't clearly distinguish from sibling tools like click_selector or find_text.

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 guidance on when to use this tool vs. alternatives. It doesn't mention that it returns page-element geometry, when an agent might need it (e.g., before clicking or scrolling), or that it complements click_selector/click_at_xy. The tab parameter is unexplained.

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