Replays recorded browser flows at browser speed without an LLM, stopping at the first changed step and returning the page so the flow can be repaired.
Replay a recorded flow at browser speed, no LLM. On failure (site changed) it stops at the failing step and returns the page so the flow can be repaired.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | ||
| name | Yes | ||
| vars | No |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden; it does disclose two valuable traits — deterministic no-LLM replay and the failure contract (stops at the failing step and returns the page). It does not disclose whether playback mutates page state, whether it requires an existing browser session/tab, or what happens on success.
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 tight sentences with zero filler; the core capability is front-loaded ahead of the failure-behavior detail. Every clause adds information an agent could act on.
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 3-parameter tool with a nested object, no annotations, and no output schema, the description is thin: it leaves vars/tab semantics and the success behavior unexplained. The failure-path disclosure is good, but an agent still can't confidently construct a call from this alone.
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% for three parameters including a nested string-map 'vars', and the description explains none of them. 'Flow' context hints that 'name' identifies the recorded flow, but the roles of 'tab' and 'vars' (presumably variable substitution) are completely undocumented.
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 and resource ('Replay a recorded flow') and adds a meaningful differentiator ('at browser speed, no LLM') that separates deterministic playback from agentic tools like fl_act. It doesn't explicitly name siblings such as fl_run_many or fl_record_start, so the boundary with the batch/recording variants is left implicit.
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 implies a recorded flow must exist first and hints at a repair loop when playback fails, but it never states when to choose fl_run over fl_run_many or fl_record_start/fl_record_stop, nor any prerequisite like an open tab. No explicit when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.