browser_guide

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

With no annotations, the description carries the burden and does disclose the key behavioral trait an agent needs: cost. It flags topic=start as 'short' and group=all as 'every command, about 25,000 tokens', which directly informs a context-budget decision. It doesn't state the return shape (prose doc text) or that calling it is side-effect free, leaving small 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?

Front-loaded with the purpose, then organized topic-by-topic so an agent can stop reading once it finds its case. The topic=commands sentence runs long with nested parentheses, but the 'all = 25,000 tokens' warning earns its space.

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?

For a zero-parameter-required documentation tool with no output schema, the coverage is reasonable but not complete: the phantom topic=skill value and the unclear topic/group relationship are exactly the details an agent could get wrong. Everything else an agent needs to pick a topic is present.

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 0%, so the description must compensate, and it largely does: it explains query ('words, e.g. "selector click"') and enumerates every group value with what 'all' yields. However, it names a topic=skill that does not exist in the enum (start, commands, gomini), a mismatch that could send an agent into an invalid call, and it never explicitly says group is only meaningful when topic=commands.

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 frames this as an on-demand usage guide ('How to use this browser, when you are unsure') and enumerates what each topic returns, which separates it from the action-oriented siblings (browser_act, browser_read, etc.). It never uses a crisp verb+resource phrase like 'return documentation', but the intent is unambiguous from the first clause.

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 gives a clear triggering condition ('when you are unsure') and routes the agent by cost: topic=start for a short loop/rules, topic=commands with a query for targeted lookup, topic=gomini for the local model. It stops short of stating when NOT to call it (e.g. don't call for routine actions already covered by the sibling tools), which keeps it below a 5.

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