sandboxed-browser-mcp

Overview Schema Source Related Servers Discussions Admin

Get text

browser_get_text

Read-only

Read the full text of a page element by its ref as plain text, in chunks, and get the offset for the next part instead of scrolling or taking screenshots.

Instructions

Returns the complete text of an element by ref (an article, a section, a long paragraph) as plain text, max_chars at a time, with a footer giving the offset of the next part. The way to read long text, instead of scrolling or screenshots.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ref": "<ref>"
    },
    "name": "browser_get_text"
  }
}

Input Schema

Name	Required	Description	Default
`ref`	Yes	Ref of the element to read (e12, f2e7 …), as browser_snapshot or browser_find showed it.
`offset`	No	Character to start at; the previous answer's footer gives the next one.
`profile`	No	Which browser profile (a separate signed-in session) to use. Leave it out for the default one; name another only when the user's task names it. Profiles: default.	default
`max_chars`	No	Most characters to return in this part.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.2.0Nov 12, 2026

addedInput schema / properties / profile

Added value: +{
+  "default": "default",
+  "description": "Which browser profile (a separate signed-in session) to use. Leave it out for the default one; name another only when the user's task names it. Profiles: default.",
+  "type": "string"
+}

Changed6 schema fields changedv1.1.0Oct 31, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / max_chars / default
```
Added value: +2000
```

changedInput schema / properties / max_chars / description

Previous value: -"Default 2000, 200 to 8000"New value: +"Most characters to return in this part."

addedInput schema / properties / offset / default
```
Added value: +0
```

changedInput schema / properties / offset / description

Previous value: -"From the previous page; default 0"New value: +"Character to start at; the previous answer's footer gives the next one."

changedInput schema / properties / ref / description

Previous value: -"Section ref, e.g. e40"New value: +"Ref of the element to read (e12, f2e7 …), as browser_snapshot or browser_find showed it."

First observedv1.0.0Oct 24, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely useful behavior beyond that: output is plain text, capped at max_chars per call, and a footer reports the offset of the next part — key for driving pagination correctly. It does not mention error cases (e.g., stale ref), but the core behavior is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the verb and return shape, then the usage rule. No redundant or filler wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description explains the return structure (plain text plus a footer with the next offset) and how to continue reading, which is exactly what an agent needs to use it correctly. Nothing essential is missing for a read-only retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented. The description reinforces the max_chars/offset relationship and the footer-to-offset loop, which is helpful, but it adds little syntax or format detail beyond what the schema states. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Returns the complete text of an element by ref'), names what counts as an element (article, section, long paragraph), and specifies the plain-text, chunked output format. It also implicitly separates itself from browser_scroll and browser_screenshot by saying it is the way to read long text 'instead of' those.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear when-to-use guidance ('The way to read long text') and names the alternatives it replaces (scrolling, screenshots). It does not state an explicit when-not case or point at browser_snapshot/browser_find as the source of refs, though the schema covers the latter.

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

Deploy Server