Delete delivery

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds non-obvious behavior: deletion works only for final 'Delivered' status, happens on all recipient devices, and is limited to tdlib/whatsapp channel messages. There is no contradiction with annotations.

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 three tight sentences: main action first, then constraints, then a practical usage trigger. There is no filler or redundant restatement of the tool name.

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 destructive operation, the description covers target channels, status prerequisites, cross-device effect, and when to invoke it. The annotations cover safety and idempotency, so nothing needed to call the tool correctly 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?

The single parameter delivery_id is fully documented in the input schema, including its origin as delivery.id from send_message. Since schema description coverage is 100%, the description need not restate or expand on the parameter.

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 a specific verb and resource: 'Delete a sent message from WhatsApp or Telegram (tdlib)'. It also adds user-facing intent ('unsend or recall a message'), making it easy to distinguish from send_message and delete_webhook.

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 explicitly says when to use it: 'Use it when the user asks to unsend or recall a message.' It also gives clear exclusions: SMS cannot be deleted, and only messages with final 'Delivered' status are eligible.

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