proofpoint_forensics_pull_messages

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

Without annotations, the description carries the transparency burden. It explicitly discloses the destructive action and its impact—'removes delivered messages from user mailboxes'—which is crucial for a mutation tool. It could add more about reversibility or permissions, but the core warning is present.

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?

Two sentences, front-loaded with the action and warning, no waste. The description is efficiently structured and easily scannable.

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 tool with no annotations, the description clearly communicates the operation and impact. It lacks some context (e.g., reversibility, prerequisites, post-pull behavior), but given the simple parameter set and clear warning, it is adequately complete.

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 100%, and the description adds no parameter-specific information. The schema already defines message_ids and reason clearly, 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 clearly states the tool's function: 'Auto-pull (search & destroy) messages from mailboxes' and explicitly notes it is a destructive operation that removes delivered messages. This distinguishes it from read-only sibling tools like proofpoint_forensics_search_messages.

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 description provides no guidance on when to use this destructive tool versus alternatives such as search_messages or quarantine_delete. It gives a warning but no use-case context or exclusions.

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