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

Annotations already declare openWorldHint, destructiveHint, non-idempotent and write access, so the bar is lower; the description still adds real value by naming the auth scope (account-bound computer:write OAuth), the local owner approval prompt, and the fact that an existing browser session is altered. Only return behavior and failure modes (e.g. no browser available) are left unstated.

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?

Three short sentences, each carrying distinct information: what it does, its side effects, and its auth/approval requirements. Nothing is repeated and the core action is front-loaded.

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 one-parameter, annotation-rich tool with no output schema, the description covers action, side effects, and access requirements. It stops short of saying what a successful call yields (a browser session, a handle, or nothing) or how errors surface.

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 100% and the single url parameter already documents 'Full HTTP or HTTPS URL; no other URL scheme.' The description's 'HTTP(S) URL' phrasing only echoes the schema, so baseline 3 applies.

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 verb and resource (open an HTTP(S) URL in the owner's computer browser) and pre-empts a likely misread with 'It is not a server-side web search.' It does not, however, distinguish itself from the nearest sibling, exza_launch_desktop_app, which an agent might reasonably pick for the same intent.

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?

The negative clause ('not a server-side web search') implies when this is the wrong tool, but there is no positive when-to-use guidance and no explicit routing between this and exza_launch_desktop_app or exza_focus_desktop_window. Usage is inferable rather than stated.

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