Resend invite

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the agent knows this is a non-destructive external-facing mutation. The description adds real value by revealing the role requirement ('grantor') and the precondition ('pending'), but says nothing about what happens to the original invite, whether a new token is issued, or rate limits on resends.

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 front-loaded sentence with no filler; the actor and precondition are stated before anything else. Its brevity is not padded, though the terseness edges into under-specification.

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 mutation tool with 4 undocumented parameters, no output schema, and openWorldHint=true, one sentence is not enough. An agent cannot tell what form/params/json_body should carry or what a successful resend returns.

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% across 4 parameters, and the description names none of them — emer_id is only inferable from the domain, and form/params/json_body are entirely opaque. With zero schema documentation the description was the only place to compensate and it does not.

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 ('resends'), resource ('emergency-access invite'), and actor ('grantor'), which separates it from vaultwarden_resend_user_invite and vaultwarden_reinvite_member. It does not explicitly contrast with vaultwarden_emergency_access_send_invite, though 'pending' implies the invite already exists.

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 word 'pending' implicitly scopes usage to invites that already exist and have not yet been accepted, and 'grantor' implies a permission prerequisite. However, no alternative tool is named and there is no explicit when-not guidance against the closely named send-invite sibling.

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