browse

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

With no annotations, the description carries the full burden and does substantial work: it enumerates the status values (done, blocked, needs_input, budget, error), explains that the tab stays open and returns a tab_id, and that the browser self-closes after idle minutes, taking its tabs with it. It does not cover authentication, permissions, or rate/cost limits, so it stops short of 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?

The content is front-loaded, with the core action in the first sentence and the arguments and status semantics following in scannable blocks. It is dense rather than padded, though the prose sections are slightly long for what remains after the status list.

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?

The tool is agentic and multi-turn, and the description covers the multi-turn mechanics (tab_id reuse, needs_input re-calls), the terminal states, and tab lifecycle. An output schema exists, and the description correctly avoids over-explaining the return payload while still noting it is markdown, so nothing essential is missing.

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 and it does: goal is explained with concrete examples plus a critical operational detail that typed text is drawn from the goal; url is described as the start page required unless continuing a tab; tab_id is described as continuing a previously returned tab. Each parameter gains meaning beyond the bare schema.

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 ('Carry out a task on a website'), the resource (Clearcote browser), and the return format ('return what the page says about it, as markdown'), which is far more than a restatement of the name. An agent can distinguish this from the sibling close_tab immediately, since browse performs work while close_tab only tears down a tab.

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?

It clearly states when to pass tab_id (a follow-up step, or after needs_input / blocked) and when url is required ('Required unless continuing an existing tab'), which maps usage onto the tool's own lifecycle. It does not explicitly name close_tab as the alternative for ending a session, so the routing guidance is strong but not exhaustive.

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