jev_browser_run

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

With no annotations, the description carries full burden. It discloses many behaviors: background operation, default/max steps, timeout, Chrome persistence, safe keys, status handling, and the limitation 'Jev does not type.' It also warns that needs_verification is not a pass. This is extensive, though it omits details like response format and side effects beyond staying open.

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 dense but efficient, with each sentence adding a distinct piece of information. It is front-loaded with purpose, then proceeds to limits, url, persistence, safe keys, and status handling. No redundancy; it reads as a tight operational spec.

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 the complexity (9 params, nested objects, no output schema, no annotations), the description covers core invocation details and re-call logic. It fails to explain several parameters and does not describe the response structure beyond statuses. It is adequate for basic use but leaves gaps for advanced configuration.

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 0%, so the description must compensate. It explains url ('Pass url to open a page'), max_steps (default 12, max 30), session_id and goal (used in re-call instructions). However, it does not explain policy, controls, tab_id, min_confidence, or allowed_origins, which are nested or non-obvious. Compensation is partial, so a middle score 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 states a specific verb and resource: 'Run one Jev chunk in background Google Chrome.' It clearly distinguishes from siblings like jev_claim_tab (tab claiming) and jev_wait (waiting). The phrase 'Pass url to open a page' further clarifies an action. However, it assumes knowledge of what a 'Jev chunk' is, which is not defined, slightly reducing clarity.

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 provides operational guidance on when to re-call the tool based on statuses (step_limit, budget, needs_verification) and conditions (task still valid). It also notes that Chrome stays open and history is kept, which helps context. However, it does not explicitly contrast with alternatives or state when not to use this tool, leaving some selection ambiguity.

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