Run JavaScript in a browser tab to extract tables, lists, or links and return the result for AI agents working through Flintrail.
Run JavaScript in the page and return the result. Fastest way to pull tables, lists or links.
| Name | Required | Description | Default |
|---|---|---|---|
| js | Yes | Function body with return, e.g. return [...document.querySelectorAll("tr")].map(r => r.innerText) | |
| tab | Yes |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It says the tool runs JavaScript and returns a result, but it does not disclose that arbitrary JS execution may mutate the page, access sensitive data, require specific permissions, or need serializable return values. This leaves significant safety and side-effect information unstated.
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 two sentences and front-loads the core action before adding a concrete use case. There is no filler, and both sentences contribute useful information for an agent deciding whether to call the tool.
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-execution tool with no annotations and no output schema, the description is incomplete. It does not explain the expected return format, how results are serialized, what 'tab' means, or the security and side-effect implications of running arbitrary code in a page. These gaps are material for correct and safe 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 coverage is 50%: the 'js' parameter has a description with an example, but 'tab' has no schema description. The tool description does not clarify what 'tab' refers to or how it should be supplied, and it adds little meaning to 'js' beyond the extraction examples already implied by the schema. With half the parameters undocumented, the description fails to compensate.
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 specific verb and resource: 'Run JavaScript in the page and return the result.' It also gives a concrete extraction use case ('pull tables, lists or links'), so the tool’s purpose is clear. However, it does not explicitly differentiate itself from siblings like fl_run, fl_snapshot, or fl_act, which could also retrieve or interact with page content.
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 phrase 'Fastest way to pull tables, lists or links' implies when to use the tool for data extraction, but there is no explicit guidance on when not to use it, prerequisites, or named alternatives. The agent can infer the extraction use case but must decide on its own how this compares to fl_snapshot or fl_network.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.