Observe browser

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

The description adds meaningful behavioral context beyond the annotations: it explicitly states the tool does not change the DOM (non-destructive), and it explains default semantics for omitted properties: 'Omitted visible/enabled mean true; omitted editable/readonly mean false.' This is valuable because the schema has no descriptions for these boolean fields. The annotations already indicate idempotentHint=true and destructiveHint=false, but the description reinforces and adds the default-value semantics, which is beyond what annotations provide.

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 three sentences, each earning its place: the first states the core function and non-mutation guarantee, the second clarifies default boolean semantics, and the third routes coordinate needs to another tool. It is front-loaded with the most important information and has no 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?

Given the tool has 5 parameters, no output schema, and 0% schema description coverage, the description does a good job of covering the key behavioral aspects: non-mutation, bounded/sparse output, and default boolean semantics. It could be more complete by explaining what 'revisioned' means and how the element catalog relates to other browser tools, but for an observation tool with idempotentHint=true, it covers the essential context an agent needs.

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. It does partially: it explains the meaning of omitted boolean parameters (visible/enabled/editable/readonly) and mentions 'bounded' and 'sparse' which relate to maxElements. However, it doesn't explain tabId, allFrames, includeHidden, or includeScreenshot in detail. The description adds some semantic value but leaves several parameters to be inferred from their names.

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 clearly states the tool's purpose: 'Return bounded page state and a sparse, revisioned element catalog without changing the website DOM.' This is a specific verb ('return') and resource ('page state' and 'element catalog'), and it explicitly distinguishes itself from mutation tools by noting it does not change the DOM. It also differentiates from coordinate-related tools by pointing to getBoundingBox.

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?

The description provides clear context for when to use this tool: when you need page state and an element catalog without DOM changes. It also gives a specific exclusion: 'Use getBoundingBox when coordinates are needed.' However, it doesn't explicitly name sibling alternatives like browser_query or browser_action, nor does it state when not to use it in favor of those. The guidance is clear but not exhaustive.

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