browser_readRead the active browser tab's title, URL, selected text, and capped readable text to answer questions about the page without a screenshot.
Title, URL, selected text and readable text of the active tab (capped). Faster and more exact than a screenshot.
| Name | Required | Description | Default |
|---|---|---|---|
| max_chars | No | Raise it (up to 50000) only if the text you need was cut off |
Changes observed during successful MCP inspections.
v0.11.1Input schema / properties / max_chars / defaultPrevious value: -12000New value: +6000Input schema / properties / max_chars / descriptionAdded value: +"Raise it (up to 50000) only if the text you need was cut off"v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds real value beyond that: it discloses the return shape and that content is capped, which warns the agent output may be truncated. No auth, rate-limit, or pagination detail is given, but the cap disclosure is the important behavioral trait here.
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 clauses, front-loaded with the return contents and then the differentiator. No filler sentences; every word 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?
For a single-parameter, read-only tool with no output schema, the description enumerates the return fields and notes truncation, and the annotation covers safety. Nothing needed to invoke it correctly is missing.
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 100% and the max_chars description ('Raise it (up to 50000) only if the text you need was cut off') already explains usage, bounds and default. The description's '(capped)' merely echoes the schema, so baseline 3 is appropriate.
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 (read) and resource (the active tab), then enumerates exactly what is returned: title, URL, selected text and readable text. The comparison to a screenshot implicitly distinguishes it from device_screenshot/look, so an agent can tell it apart from siblings.
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?
The clause 'faster and more exact than a screenshot' gives a clear selection signal against the screenshot siblings. It stops short of explicit when-not guidance or naming alternatives such as browser_elements for structured/DOM data, so it is clear context without exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.