fl_act

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it usefully discloses that a fresh snapshot comes back after the batch. However, it says nothing about failure semantics (does one bad action abort the rest?), whether actions execute sequentially, or implicit waits/load behavior — all critical for a multi-step mutating tool.

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 front-loaded sentences, the batching directive immediately after the capability statement, zero filler. The parenthetical action list is dense but earns its space by conveying scope.

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 high-complexity tool (16 action types, ~20 nested fields, no annotations, no output schema), the description covers purpose and batching but leaves the agent to infer tab targeting, snapshot result format, and error behavior from the schema 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 coverage is only 40%, so the description needs to compensate: the enumerated examples map loosely to the 'do' enum values (click, fill, wait). But the top-level 'tab', 'max', 'text', and 'snapshot' parameters and most of the nested action fields (ms, role, exact, label, placeholder, headers) are unexplained in both places.

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: run several browser actions in one call, with concrete examples (fill a form, click, submit, wait, extract) and a stated return ('one fresh snapshot'). It clearly differs from siblings like fl_snapshot or fl_extract, though it never names an alternative tool explicitly.

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?

'Always batch as many actions as possible: one call beats ten' gives an unambiguous usage policy and implicitly discourages one-action-per-call churn. It stops short of naming when NOT to batch (e.g., when an intermediate result is needed to decide the next action) or naming the sibling tools to use instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.