Create Historical Reply Scan

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

The description adds behavioral context beyond annotations: it specifies atomicity, snapshot consistency, and 30-day retention. Annotations already indicate idempotentHint=true (consistent with 'complete' and 'snapshot-consistent') and destructiveHint=false. The description enriches transparency without contradicting annotations. However, it does not detail any side effects or permission requirements.

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 exceptionally concise: two sentences that convey the core action, atomicity, and retention. Information is front-loaded with the primary purpose, and every word serves a purpose. No extraneous details.

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 tool has 4 parameters, 2 required, and an output schema, the description is minimally complete: it covers the action and retention but lacks parameter explanations, prerequisites, and usage guidance relative to siblings. The output schema and annotations partially compensate, but the description alone leaves gaps about parameter semantics and when to create vs retrieve scans.

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 only 25% (only idempotency_key has a top-level description). The description mentions 'date window' hinting at after/before, and 'reply-needed threads' hinting at mailbox_ids, but does not explain parameter formats, the meaning of 'reply-needed threads' in relation to the parameters, or the required vs optional nature. The schema itself provides minimal descriptions for mailbox_ids items and idempotency_key, but the tool description adds insufficient value.

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 purpose: 'Atomically capture a completed, snapshot-consistent set of reply-needed threads in a date window.' The verb 'capture' and resource 'reply scan' are specific, and the mention of atomicity, snapshot consistency, and date window distinguishes it from sibling tools like get_reply_scan or list_reply_scan_results, which retrieve or list scans.

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 tool versus alternatives, such as when to create a new scan versus retrieving existing ones. There are no exclusions, prerequisites, or hints about context (e.g., 'use this to take a point-in-time snapshot'). Siblings like get_reply_scan and list_reply_scan_results exist but are not referenced.

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