Extract plain readable text from the active browser tab to access articles, rules, and docs without element table complexity.
Read the target tab as plain readable text (article/prose content), for pages where you need the text itself — rules, docs, articles — rather than the element table.
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | ||
| max_chars | No |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already signal read-only and open-world behavior. The description adds that the tool extracts prose-like readable text rather than element/table data, which is meaningful behavioral context. It does not mention truncation behavior or max_chars effects, but the readOnlyHint lowers the burden for safety-related disclosure.
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?
The description is a single well-structured sentence with the action and resource front-loaded. Every clause adds value: what it reads, what format it returns, and when it should be preferred.
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?
The core read behavior and output format are adequately described, and the tool is simple with only two optional parameters. However, with no output schema and no parameter documentation, the description still leaves tabId and max_chars semantics underspecified, so it is not fully complete.
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 0%, so the description must compensate, but it only loosely references the 'target tab' and says nothing about max_chars. An agent cannot infer that tabId identifies a specific tab or that max_chars caps the returned text length.
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?
The description uses a specific verb ('Read') with a specific resource ('target tab') and clearly defines the output as 'plain readable text (article/prose content)'. It also distinguishes the tool from the 'element table' mode, so an agent can tell what this tool is for at a glance.
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?
It states when to use the tool: 'for pages where you need the text itself — rules, docs, articles — rather than the element table'. This gives clear context and an implicit exclusion, though it does not explicitly name a sibling tool like browser_observe as the alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.