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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it lists exactly what is destroyed, explicitly enumerates what is preserved (call history, billing, traces, outreach dedup), states the operation is NOT undoable, and discloses the live-sync caveat where a thread can be re-created.

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?

Front-loads the irreversible-destruction warning and the confirm requirement, then layers what is deleted, what is kept, and the channel nuance. Despite its length, nearly every sentence carries decision-relevant information and none is filler.

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, multi-target tool with no output schema, the description covers the confirm gate, the single/bulk parameter choice, the full set of side effects, preserved data, and the channel-dependent permanence distinction. Nothing an agent needs to invoke it safely is missing.

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 confirm, thread_id, thread_ids and in_workspace are already documented in the schema, and the description largely restates the OR-relationship and the confirm gate. With the schema doing the heavy lifting, a baseline 3 is appropriate; the description offers no additional syntax or format detail beyond what is already structured.

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+resource (permanently delete conversation thread(s)) plus the exact scope of collateral deletion and the required confirm gate. It is clearly distinguishable from siblings like threads_update or messages_delete because it enumerates what is removed (messages, tags, assignments, drafts, reminders, RAG chunks).

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?

Gives concrete when-to-use guidance via the thread_id (single) vs thread_ids (bulk) selection and the confirm=true prerequisite. It also explains channel-dependent behavior (live synced channels only clear the local copy; livechat/voice/test/duel are permanent), which is strong context, though it never names an explicit alternative tool for narrower deletions.

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