Resend device invite

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=true, so the safety/state profile is covered structurally. The description adds nothing beyond that: it does not say whether the previous invite/link is invalidated, whether a new expiry is issued, or whether the operation can fail for already-accepted invites — notably the non-idempotent hint goes unexplained.

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 short sentence with the action front-loaded and no filler. It is efficient, though arguably under-specified rather than optimally terse.

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 one fully documented parameter and no output schema, the mechanical surface is covered. However, for a state-changing, non-idempotent operation the description omits side effects and return expectations, leaving the minimal viable picture rather than a complete one.

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 100% (inviteId documented as 'The device invite ID to resend'), and there is only one parameter. The description adds no format, sourcing, or validation detail beyond the schema, so the baseline of 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?

The description states a specific verb ('resend') and resource ('device invite email'), so an agent immediately knows the operation. It implicitly distinguishes itself from sibling resend tools like tailscale_resend_user_invite and tailscale_resend_contact_verification by naming 'device invite', though it never explicitly contrasts them.

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 guidance on when to use this versus alternatives, nor any precondition such as the invite needing to be pending or unexpired. The agent must infer the trigger condition (an invite that was not received or expired) entirely on its own.

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