Reads the current Safari page as an outline and assigns [ref_N] IDs to interactive elements, so you can click, fill forms, or scroll using those references.
Read the page as an outline. Interactive elements get [ref_N] ids usable with click / form_input / scroll.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | Tab id "windowId:tabIndex" from tabs_list. Omit for the active tab of the front window. | |
| filter | No | all | |
| max_chars | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose the output shape (outline) and the ref_N linking mechanism. However it says nothing about truncation via max_chars, what 'outline' omits (e.g. plain text, hidden nodes), or that omitting `tab` targets the front window's active tab.
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 core action and then the actionable detail about ref ids and which follow-up tools consume them. Nothing is wasted.
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 structure and truncation more fully. It covers the ref mechanism adequately but leaves the filter and size-limit parameters — and any indication of content being cut off — undocumented, so an agent can call it but cannot predict the response well.
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 only 33%: `tab` is documented in the schema, but `filter` and `max_chars` have no descriptions there. The description does not compensate at all — it never mentions the all-vs-interactive filter or the character cap / truncation behavior, both of which materially change the result.
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 ('Read the page as an outline') and adds the key output trait: interactive elements carry [ref_N] ids. It implicitly distinguishes itself from get_page_text by promising an outline rather than raw text, but never names that sibling.
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?
Usage is implied rather than stated: an agent can infer this is the entry point for obtaining refs before calling click / form_input / scroll. There is no explicit 'use this instead of get_page_text when...' routing or any exclusion, so a caller must infer the choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.