Create a browser guest link

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

Annotations declare this is a non-read-only, non-destructive, non-idempotent, closed-world mutation, and the description adds real context on top: owner-only authorization, local-state-only persistence, Funnel availability reported separately, and bearer tokens masked unless explicitly requested. It stops short of describing what a repeated call does or how grants interact with existing ones.

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?

Four short, front-loaded sentences: the owner-only constraint leads, followed by scope, state behavior, and token visibility. Telegraphic style occasionally compresses meaning, but no sentence is filler.

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?

With an output schema present, return values need not be explained, and the description covers authorization, persistence scope, and token exposure. Gaps remain around the public flag's effect and the consequences of repeated non-idempotent calls, but the essentials for correct invocation are 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 only 50%: the 'for' parameter is exhaustively documented and 'pin'/'print_link' have notes, while 'app', 'label', and 'public' have none. The description adds 'for one app' and echoes the token-masking behavior tied to print_link, but does not compensate for the undocumented label/public parameters.

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 names a specific verb and resource (creating browser guest grants) and scopes it to one app, so the agent knows this is the creation step in the guest lifecycle. It does not explicitly differentiate from siblings like guest_list, guest_revoke, guest_show, or invite_user, but the action is unambiguous.

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?

'Owner-only' establishes a caller precondition, and the note that no OIDC or tailnet account is required frames the context. However, there is no explicit when-to-use guidance against alternatives such as invite_user, people_grant, or share, so routing must be inferred from the name.

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