exchange_remove_mailbox

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'Remove' and the parenthetical 'delete' correctly signal a mutating/destructive operation, but the description does not state whether the mailbox data is purged, whether the operation is reversible, whether the associated Active Directory user is affected, or what the difference between 'disable' and 'delete' actually is. This is a significant gap for a destructive tool.

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?

The description is compact and front-loaded with the action verb, containing no filler words. However, the brevity crosses from conciseness into under-specification for a destructive tool with two undocumented parameters; six words of description are not an appropriately sized payload for the decisions an agent must make.

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?

Given the absence of annotations, an output schema, and any parameter documentation, the description needed to supply the semantics of the destructive operation and its parameters. It only covers the action itself. Missing are the meaning of 'permanent', the expected identity format, the default behavior, the side effects on user/mailbox data, and any return value, leaving an agent unable to call the tool correctly with confidence.

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 0%, so the description must compensate, but it explains neither parameter. 'identity' could be a UPN, email address, GUID, or distinguished name — unspecified. 'permanent' is a boolean whose semantics are highly ambiguous: does false mean a soft-delete that can be restored, or a disable that keeps the mailbox object? The description's '(disable/delete)' hints at this distinction but never connects it to the parameter.

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 uses a specific verb ('Remove') with a clear resource ('mailbox') and the parenthetical '(disable/delete)' elaborates on what the action entails. It is readily distinguishable from the sibling set: exchange_create_mailbox, exchange_set_mailbox, and exchange_get_mailbox are clearly different operations. It loses the fifth point because the description never explains how 'disable' and 'delete' differ behaviorally or which is the default.

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?

No guidance is given for when to use this tool versus alternatives. With over 35 siblings including exchange_set_mailbox and exchange_create_mailbox, an agent receives no hint about whether this is the right tool for deprovisioning a user, hiding a mailbox, or permanently purging data. No exclusions, prerequisites, or alternative names are mentioned.

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