Re-reads a browser tab to return interactive elements with refs, headings, and the start of page text, enabling agents to inspect and act on the current page state.
Re-read a tab: interactive elements with refs, headings and the start of the text.
| Name | Required | Description | Default |
|---|---|---|---|
| max | No | Max interactive elements listed (default 150). | |
| tab | Yes | ||
| text | No | Characters of page text to include (default 600, 0 for none). |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden: it never states that this is a read-only operation, how refs are scoped/stable, whether refs are the handles fl_act expects, or what the cost/size of a snapshot is. It lists return contents but not behavior.
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?
A single short sentence, front-loaded and free of padding. It is efficient rather than padded, though the terseness leaves key facts unstated rather than the phrasing being wasteful.
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 annotations, no output schema, and an undocumented required parameter, the description should compensate more: the output is only loosely sketched (no shape, no ref format) and the link from refs to fl_act is left implicit. An agent would have to guess at the calling contract.
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 67% (max and text are documented, the required 'tab' is not). The description adds nothing about any parameter, and in particular does not say where the 'tab' identifier comes from (presumably fl_tabs) or how max/text trade off against snapshot size.
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?
It does name the deliverable — interactive elements with refs, headings, and the start of the page text — which is a specific enough resource. But the lead verb 'Re-read a tab' is cryptic about what is actually being captured (a DOM/accessibility snapshot), and it gives no signal distinguishing it from sibling fl_extract or fl_screenshot.
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?
'Re-read' hints that this is called after an action changes the page, but there is no explicit statement of when to use this versus fl_extract (text extraction), fl_screenshot (visual), or fl_tabs (listing tabs). No prerequisites or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.