neuron_vision_act

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

With no annotations, the description must disclose behavior itself, and it does explain the underlying flow: screenshot, analysis, then click/type via coordinates or best-match selectors. However, it does not mention side effects, whether actions are reversible, failure modes, or permissions, which is notable for an action-taking 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?

The description is compact and front-loads the core capability and key differentiator. The process sentence and usage condition each add value, with no filler or redundant restating of the tool name.

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 sufficient for choosing and roughly invoking the tool, but because there is no output schema, it leaves the return behavior unspecified—such as whether the agent receives a screenshot, a click confirmation, or an action result. Some limitations and prerequisites are also unstated.

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 all three parameters. The description adds useful signal about instruction being natural-language driven and provides examples, but it doesn't materially go beyond the parameter descriptions.

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's specific capability: taking a viewport screenshot and performing an action based on visual understanding. It explicitly distinguishes itself from CSS-selector/DOM approaches, which separates it from sibling tools like neuron_click, neuron_type, and neuron_query_dom.

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?

It gives an explicit trigger condition: 'Use when you don't know the page structure or selectors keep breaking.' This is clear and actionable, but it does not name specific alternative tools or provide explicit when-not-to-use guidance, so it stops short of the top score.

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