jev_browse

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

With no annotations provided, the description carries the full burden and does a good job: it discloses read-only behavior, the max_steps cap, and the return contents (session_id, visible page evidence, recent actions). It also warns against personal/financial data entry. It does not mention side effects like server-side state, cookies, or rate limits, but it covers the most critical safety and operational traits.

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 short paragraphs with no filler. The core purpose and primary constraint are front-loaded, and every sentence provides actionable information: what it does, when to use, how executions are bounded, what is returned, and what to avoid.

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?

Given three parameters, no annotations, and no output schema, the description covers the essential invocation context: URL, goal, max_steps, return values, and usage boundaries. It lacks a precise definition of 'visible page evidence' or 'advance,' and does not explain how to handle already-open sessions, but the provided information is sufficient for a competent agent to invoke the tool correctly in most cases.

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?

With 0% schema description coverage, the description must compensate. It adds meaningful context for max_steps by giving a range (1–30) and explaining its role, and it implies goal is a browsing objective like 'finding, filtering, or opening products.' However, url is not explicitly described beyond the phrase 'public website,' and the two required parameters are not fully disambiguated, so the compensation is partial.

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 ('Start a new browser session') plus the goal ('advance a read-only browsing goal'). It clearly differentiates itself from siblings like jev_status and jev_stop by emphasizing session creation and read-only browsing, and from jev_extract_products by focusing on browsing rather than extraction.

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 gives explicit use cases ('finding, filtering, or opening products') and strong exclusions ('Do not use it for login, checkout, payment...'), which is more than a minimal viable. However, it does not name any alternative sibling tools or specify when to prefer them, so it stops short of the full when/when-not/alternatives guidance.

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