Locate visible Safari page elements by role, name, or text query and return up to 20 references for targeted interaction.
Find visible elements whose role/name/text contains the query. Returns up to 20 refs.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | Tab id "windowId:tabIndex" from tabs_list. Omit for the active tab of the front window. | |
| query | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden but does disclose two real behavioral facts: only visible elements are matched, and results are capped at 20. It does not say what happens when more than 20 elements match (silent truncation?), whether matching is case-insensitive, or whether refs expire or are reusable across calls.
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?
Two short sentences, front-loaded with the matching semantics and ending with the result limit. Nothing is redundant and every clause carries information.
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?
With no output schema and no annotations, the description should explain the return shape more fully. It says results are "refs" capped at 20 but never describes what a ref looks like or whether role/name come back with it, leaving the agent partially blind on a two-parameter tool whose output is the whole point.
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 coverage is 50%, with `query` documented only as a bare string in the schema; the description compensates by explaining that it is substring-matched against role, name, and text. The `tab` parameter is well documented in the schema itself, so the remaining gap is minor.
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 and resource ("Find visible elements") plus the matching dimensions (role/name/text) and the result cap. This is enough to distinguish it from siblings like get_page_text or read_page, which retrieve content rather than locate interactable elements, though the description never names those siblings explicitly.
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 statement of when to use this tool versus read_page, get_page_text, or tabs_list, and no exclusions or prerequisites. The mention of "refs" implies a find-then-click workflow, but the agent must infer that.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.