browse

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

No annotations are provided, so the description carries the full burden. It does disclose two useful behavioral facts: the loop terminates on goal satisfaction or a step limit, and the return includes the last numbered screenshot. But it omits critical behavior for an autonomous agent — whether it can mutate state (allow_writes defaults false), cost/latency expectations, and what happens on failure — leaving major gaps.

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?

A single compact sentence with the terminating condition front-loaded and no wasted words. It is appropriately sized for a one-line summary, though the brevity is a consequence of under-specification rather than deliberate economy.

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?

This is a complex autonomous tool with 5 parameters, no annotations, no output schema, and 0% schema coverage, yet the description is one sentence. It partially covers the return value ('last numbered screenshot') but leaves parameter meaning, write permissions, and failure behavior unexplained — insufficient for a tool of this complexity.

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% across 5 parameters, so the description must compensate and largely does not. It obliquely covers 'goal' and 'a limit' (max_steps), but says nothing about facts, start_url, or the significant allow_writes flag, whose false default materially changes tool behavior. Three of five parameters are effectively undocumented.

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 conveys that this is an autonomous multi-step loop ('run the whole loop until the goal is met') that returns a final screenshot, which contrasts implicitly with the primitive siblings (click, type, goto). However, it never names the resource being browsed — no mention of a browser, web page, or session — so the agent must infer the domain from sibling names. Purpose is vague rather than specific verb+resource.

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?

There is no explicit guidance on when to use this tool versus chaining the granular siblings (look, click, type, scroll). The phrase 'the whole loop' hints that it replaces manual stepping, but no condition or exclusion is stated. An agent gets no instruction about prerequisites or when the primitive tools are preferable.

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