Delete a WhatsApp message

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

Beyond the annotations' destructiveHint=true, the description discloses that the retraction is "visible to everyone in the chat" (blast radius), that only the linked account's own messages are eligible (auth/permission limitation), and the 2-day time window. These are exactly the kinds of concrete behavioral details — what gets destroyed and under what constraints — that the annotations' booleans cannot express. No contradiction exists between the warnings and the readOnlyHint=false/destructiveHint=true flags.

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?

Three tightly written sentences, each earning its place: the operation itself, the destructive warning with user-confirmation protocol, and the constraints. The most critical safety information ("DESTRUCTIVE") is front-loaded immediately after the verb, exactly where an agent will see it before calling the tool.

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 2-parameter destructive operation with no output schema, the description covers all essential call-time knowledge: side effects (visible to all), pre-conditions (own message, within 2 days), and user-consent requirements. The only minor gap is that it doesn't describe error behavior or what happens with the default for_everyone=false when a user expects a private delete — but the schema annotation largely covers that.

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% — both message_id and for_everyone are fully documented with provenance guidance and semantic clarifications (e.g., "WhatsApp supports no other kind of delete here"). The description adds no parameter-specific meaning beyond the schema, but per the baseline rule, 3 is appropriate when the schema does the heavy lifting.

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?

"Retract a message" is a specific verb-plus-resource that unambiguously states a delete operation, reinforced by the title "Delete a WhatsApp message." The description is clearly distinct from siblings like edit_message or forward_message because the DESTRUCTIVE warning and visibility consequence leave no doubt this is a removal, not a modification, operation.

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 gives explicit exclusions — "only works on messages the linked account sent" (privilege constraint) and "only within 2 days of sending" (temporal constraint) — which tell an agent when not to attempt deletion. It also includes workflow guidance ("confirm with the user first"). However, it doesn't name alternatives like edit_message for cases when the 2-day window has passed, which would elevate it to a 5.

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