Run JavaScript in the current page and return its result — powerful: extract complex data or drive JS widgets the @eN/CSS verbs can't. Runs in the page's sandbox (not the host); navigation stays SSRF-guarded.
| Name | Required | Description | Default |
|---|---|---|---|
| js | Yes | JavaScript expression/IIFE to evaluate in the page | |
| browser_id | Yes | from browse_open |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate the tool is not read-only, idempotent, or destructive, but the description adds important security context: it runs in the page's sandbox and is SSRF-guarded. However, it does not disclose potential side effects like page state modifications, error behavior, or timeouts. Given the lack of annotation support, the description should be more thorough about 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?
The description is extremely concise—two sentences that are front-loaded with purpose and differentiation, followed by a crucial security note. Every sentence adds value without redundancy. It is appropriately sized for the tool's complexity.
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 description is clear but lacks completeness given the tool's power and complexity. It does not explain output format (e.g., JSON, string), error handling, or timeouts. With no output schema, the agent may misinterpret the return value. While the security context is helpful, the description should provide more detail for reliable tool invocation.
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%, so the schema already documents both parameters. The description adds no new parameter-level information; it only restates that JavaScript is executed. Thus, the description does not significantly enhance the agent's understanding of the parameters beyond the schema.
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 clearly states the tool runs JavaScript in the current page and returns the result. It explicitly distinguishes itself from other browse tools by mentioning it can handle tasks that @eN/CSS verbs cannot, such as extracting complex data or driving JS widgets. This provides a specific verb-resource-action pair and differentiates it 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 description gives clear guidance on when to use this tool: for extracting complex data or driving JS widgets that other browse verbs (like browse_extract or browse_click) cannot handle. It implies this is the tool of choice for javascript-heavy interactions. However, it does not explicitly state when not to use it or provide alternatives beyond the contrast with @eN/CSS verbs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools serve similar purposes (e.g., web_read vs browse_read, web_discover vs browse_discover, research vs web_search + browse). Descriptions help differentiate, but the overlap is notable.
Most tools use a consistent verb_noun snake_case pattern (e.g., archive_message, browse_navigate). Minor deviations like standalone 'browse' and 'identity' are acceptable.
57 tools is very high for a single server, even with discover_tools. The broad domain coverage does not justify the count; it feels overloaded.
Covers identity, memory, browsing, human tasks, errands, messaging, and research comprehensively. Minor gaps might exist (e.g., no explicit agent-to-agent contract tools), but core workflows are well-supported.