browser_run_task

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

With no annotations, the description carries the full burden and does well: it discloses duration ('takes minutes, not seconds'), progress reporting, autonomous step planning, mid-task pausing on login/captcha/payment with human handoff and resumption, and the vision-model dependency. It does not clarify failure behavior or what happens when maxRounds is exhausted, which keeps it below a 5.

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?

Four sentences, each earning its place: purpose first, then duration expectation, then input style, then human handoff, then the model prerequisite and cheaper alternative. Nothing is repeated from the schema and the most decision-relevant facts are front-loaded.

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 an 11-parameter, long-running agentic tool with no annotations and no output schema, the description covers the important behavioral surface (duration, pausing, resumption, model requirement). The one gap is that with no output schema it never says what a completed run returns or how progress/errors are surfaced, which would matter for a caller parsing results.

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 91%, so the baseline is 3, but the description adds real meaning for the `task` parameter ('describe the task in plain language; it works out the steps itself') and explains the resume model that titles history/tabId/windowId/humanReply are used for. That goes beyond restating schema text.

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?

States a specific verb and resource: 'Carry out a whole web task in a real browser and report what happened.' It explicitly frames the tool as end-to-end task execution rather than a primitive action, which cleanly separates it from the many browser_click / browser_navigate siblings.

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?

Gives explicit when-to-use ('a whole web task'), when-not-to-use ('for a small job you can drive the browser yourself'), the alternative siblings by name (browser_take_snapshot / browser_click / browser_input_text), and the prerequisite (vision model via EMBIODY_VLLM_*). It also documents the human-handoff path for login/captcha/payment.

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