Query page elements

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

Annotations are absent, so the description carries the full disclosure burden. It does add one useful behavioral trait by explaining the tool does not return full page text, which prevents a reasonable misunderstanding. However, it does not state whether the tool is strictly read-only, what the return shape is, whether it waits for page content, or how it handles pages with no matching elements, leaving the agent to infer important behavioral traits.

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 one short sentence with no filler, and the meaningful behavioral constraint 'without returning full page text' is included. It loses one point for restating the title's basic purpose before adding the new information, but it is still concise and front-loaded.

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 8 mostly optional parameters and no annotations or output schema, the description is minimal and does not fully define how the tool behaves at the boundaries. It does not explain how selector, role, text, and visibility relate to one another, what the returned elements look like, or what constraints exist around tab/session/frame addressing.

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 only 38%, so the description should compensate for undocumented parameters. It covers four of them by listing 'selector, role, text, and visibility', which gives semantic meaning to `selector`, `role`, `text`, and `visible`. It does not explain how multiple criteria interact (e.g., AND or OR) and says nothing about `limit` semantics, so parameter behavior is only partially defined.

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 states a specific verb ('Find'), a specific resource ('elements'), and explicit search dimensions: 'selector, role, text, and visibility'. It also adds a discriminating constraint, 'without returning full page text'. It is clear what the tool does, though it does not name a sibling tool (e.g., extract_elements or visible_snapshot) so an agent must infer the exact boundary.

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?

There is no explicit guidance about when to use this tool versus alternatives such as extract_elements, visible_snapshot, or wait_for. No usage condition, prerequisite, or 'use this when X' is provided. The only hint is the negative 'without returning full page text', but no direct comparison or sibling differentiation is offered.

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