Unsend a message

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that: the 2-minute time limit, the recipient-visible effect ('disappears for the person'), and irreversibility ('can't be undone'). It omits what happens on failure — e.g., an expired-window error or permission requirements — which would complete the picture.

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 short sentences, zero filler, with the time constraint and the irreversibility warning both front-loaded where an agent will see them. Every clause carries operational weight.

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 one-parameter, no-output-schema tool, the description covers the essentials: what it does, the time limit, the recipient effect, and irreversibility. The remaining gap is the undocumented message_id and failure behavior, which is meaningful but modest for a tool this simple.

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?

The single required parameter, message_id, has 0% schema description coverage, so the description carries the full burden and says nothing about it — not where to obtain the ID, nor whether it is the sender's or recipient's copy, nor what happens if the ID belongs to another conversation. The semantics are only weakly inferable from the verb.

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 and resource ('Take back an iMessage you sent') with a clear scope qualifier (within 2 minutes), so an agent can distinguish it from siblings like edit_message or send_message. It does not explicitly name an alternative, but the retraction semantics are unambiguous.

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 one concrete usage condition — the 2-minute window — which is genuinely action-guiding. It stops short of saying what to do when that window has passed (e.g., use edit_message instead) or whether the caller must be the original sender, leaving routing decisions to inference.

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