browser_evaluateExecute custom JavaScript in a page context to retrieve information or interact with elements. Optionally provide a selector to pass the matched element into the script.
Run JavaScript in the page context.
| Name | Required | Description | Default |
|---|---|---|---|
| script | Yes | ||
| selector | No | Matched element passed as first arg to script. | |
| sessionId | Yes |
Changes observed during successful MCP inspections.
v0.1.14Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions execution in the page context but does not warn that arbitrary JavaScript can mutate the page, trigger network requests, navigate away, or have other side effects, nor does it describe return-value behavior or error conditions.
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, front-loaded sentence with no filler. It communicates the core action immediately, which is strong conciseness even though other dimensions need more content.
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 JavaScript evaluation tool with no annotations, no output schema, and multiple related browser tools, this description is too sparse. It omits side-effect risks, return serialization, selector behavior, and the meaning of sessionId, leaving agents to infer critical invocation details.
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 only 33%, and the description adds no parameter-level meaning beyond the script context. The selector parameter has a schema description, but script and sessionId remain undocumented, and the description does not explain how script and selector interact.
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 states a clear action and target: run JavaScript in the page context. It distinguishes the tool from navigation, clicking, and snapshot tools, though it does not explicitly contrast it with browser_dom_query or other sibling tools.
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?
There is no guidance on when to use this tool versus alternatives like browser_dom_query or browser_generate_locator. The description implies use when arbitrary JavaScript execution is needed, but it does not provide exclusions, prerequisites, or comparison with related browser tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.