run_browsing_task

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

With no annotations provided, the description bears full responsibility for disclosing behavioral traits. It mentions the agent 'operates it like a person' and returns a task_id, but it does not disclose whether the tool is destructive, requires authentication, has rate limits, or what the scope of 'browsing' entails (e.g., navigation, form filling, scraping). This leaves significant behavioral ambiguity.

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 short (3 sentences) and front-loads the purpose. However, it sacrifices completeness for brevity, omitting critical parameter details and usage context. It is not overly verbose, but the conciseness is at the expense of utility.

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 8 parameters (2 required), the presence of an output schema, and many sibling tools, the description is incomplete. It fails to explain how to use webhooks, polling, authentication, or output_fields. It also does not differentiate from the similar sibling run_research_task, leaving the agent without sufficient context for correct invocation.

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 0%, so the description must compensate. It only touches on 'task' (via example) and 'browser' (hint for local), but ignores the other 6 parameters (start_url, max_steps, webhook_url, require_auth, output_fields, webhook_format). No details on data types, constraints, or semantics beyond what the schema already shows.

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 executes a one-time web browsing task and uses a navigator agent that operates a browser like a person. It returns a task_id for polling, which defines the resource and action. However, it does not explicitly differentiate from sibling tools like run_research_task, so it loses some clarity for distinction.

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 an example ('list employees') and a usage hint for setting browser='local' to use the desktop app with logged-in sessions, which implies when this mode is appropriate. However, it lacks explicit guidance on when to use this tool versus alternatives (e.g., run_research_task, create_scout) and does not mention when not to use it.

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