Close the browser

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious state information — the Google login persists in the profile — which tells the agent session auth survives the close; it stops short of clarifying whether unsaved page edits are lost.

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?

Two short sentences, action first and the persistence caveat second; nothing is padded or redundant.

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 teardown tool with no output schema, the definition covers the essential outcome and the one surprising side effect. Only the fate of unsaved in-progress work is left unstated.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate and it correctly refrains from inventing options.

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?

'Close the controlled browser' names a specific verb and resource, and the 'controlled browser' phrasing ties it to the automation session rather than an arbitrary browser, which separates it from siblings like gsites_open and gsites_screenshot.

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?

Usage is only implied: an agent can infer this ends the automation session, but the description never says when to close (end of task, before relaunch) or whether gsites_open must be called again afterwards. No alternatives or exclusions are named.

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