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

Annotations already declare destructiveHint=true, but the description adds value beyond that: 'Returns no body' clarifies the response behavior, 'This cannot be undone' emphasizes irreversibility, and the shared-account warning explains a non-obvious consequence. These details are not present in the annotations or schema, so the description carries meaningful extra disclosure.

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, front-loading the core action and key warning, then adding the alternative. Every sentence adds value: the action, the irreversibility, the shared-account implication, and the alternative tool. No fluff or redundancy.

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 destructive operation with no output schema and annotations covering safety, the description covers all essential aspects: what it does, that it returns nothing, that it cannot be undone, that the message might belong to another caller, and how to achieve a non-destructive alternative. An agent has everything needed to decide whether to call it.

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%, so all three parameters (inbox_id, message_id, Authorization) are already documented. The description does not add any parameter-specific nuance beyond what the schema provides; the shared-account warning is contextual but not parameter-level. Baseline 3 is appropriate when the schema handles parameter documentation.

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 opens with 'Permanently deletes one message' – a precise verb and resource. It distinguishes itself from sibling tools like delete_agentmail_inbox_thread and delete_agentmail_inbox_draft by explicitly stating it targets a single message, and it reinforces the permanence, which is a clear differentiator.

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?

Provides explicit when-not-to-use guidance: 'To hide a message from a workflow without destroying it, relabel it with `patch_agentmail_inbox_message` instead.' It also warns about the shared-account context, telling the agent that the message may not belong to the caller, which is critical for deciding whether deletion is appropriate.

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