Navigate a browser with Jev

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals stopping conditions (goal met, stuck gate, budget exhaustion), and lists returns (final page, step trace, errors, token usage, screenshot). However, it does not mention that the agent may interact with the page (e.g., typing, clicking) as indicated by the allow_typing parameter, which is a side effect. It also doesn't explicitly state that this is a potentially long-running or costly operation, though it mentions budgets and token usage. This partial disclosure merits a 3.

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 long sentence but is packed with essential information: it front-loads the core purpose and then enumerates return values. It is not verbose and every clause adds value, though the sentence is somewhat run-on. Slightly better formatting could improve readability, but it is appropriately concise.

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 tool with 8 parameters, no output schema, and no annotations, the description covers the key behavioral aspects: stopping conditions, return payloads, and error capturing. It does not detail the structure of the step trace or token usage report, but the schema covers parameter details. Overall, it gives enough context for an agent to understand what will happen and what it will receive, though a bit more on side effects would push it to 5.

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 fully documents all 8 parameters, including formats, defaults, and constraints. The description adds no extra semantic value beyond what the schema provides, so the baseline 3 is appropriate.

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 function: 'a Jev-driven agent navigates a real headless browser until the goal is met...' It specifies the verb (navigate), the resource (real headless browser), and the stopping conditions, making it unambiguous what the tool does. Since there are no sibling tools, differentiation is not required, but the description is specific enough to stand alone.

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 usage: 'Give a task and a start URL' clearly indicates the intended invocation. It does not explicitly state when not to use it or list alternatives, but with no sibling tools, this is acceptable. The context of browser automation is evident from the description.

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