run_browser_use_task

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

No annotations are supplied, so the description carries the full burden — and it does most of it: it discloses the URL scoping/enforcement behavior, the runtime prerequisite (pip install browser-use plus an LLM API key), and that authenticated pages need cookies/login. What's missing is failure/cost behavior (what happens on step exhaustion, latency, whether it can mutate state).

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?

Front-loads the purpose, then routing guidance, then prerequisites, then examples — a sensible information hierarchy. The example lines are justified because they define what a valid `task` string looks like; only mild redundancy in the two-part requirements sentence.

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?

An output schema exists, so return values need no explanation, and the description covers scope, prerequisites, and sibling routing. It falls short only on the non-task parameters, which is a real gap given 0% schema coverage but not fatal for a tool whose primary input is a natural-language prompt.

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 is responsible for the four parameters, but it only illustrates `task` via two examples. `model`, `headless`, and `max_steps` receive no explanation beyond their bare titles and defaults, leaving an agent to guess at the cost/time tradeoffs of max_steps or when headless should be false.

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 action (run an autonomous browser-use agent) for a specific class of work (complex multi-step tasks on Infinite Backlog). It explicitly contrasts itself with the sibling deterministic tools (open_site, click, fill, etc.), so an agent can route without opening a schema.

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 routing guidance: 'Prefer the deterministic tools for simple reads/clicks' and reserve this for complex multi-step tasks. Also states a hard scope boundary (infinitebacklog.net only; refuses tasks containing non-IB URLs), which functions as an explicit when-not-to-use rule.

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