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

Annotations only declare destructiveHint=true; the description goes well beyond that by explaining that words and files disappear for everybody, that a «deleted» placeholder remains so replies still resolve, that the action is irreversible, and that it is restricted to the caller's own messages. This is exactly the operational context an agent needs before invoking a destructive tool.

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?

A single front-loaded sentence covering effect, side effect, irreversibility, and permission, with no filler. Every clause carries distinct information.

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 tool with no output schema, the description covers consequences, persistence semantics, and authorization scope. It omits only what the call returns (e.g. the deleted message id or success flag), a minor gap.

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%, so the schema already documents chatId and messageId. The description nonetheless adds a real constraint on messageId — it must be a message the caller wrote — which the schema only hints at.

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 (delete) and resource (a chat message you wrote), plus an ownership scope that separates it from generic message operations. It does not explicitly name edit_chat_message as the non-destructive sibling, so differentiation is inferred rather than stated.

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?

'As the screen does' and 'Only your own message' imply when the tool applies, and 'Cannot be undone' signals the risk profile of the choice. However, no alternative is named (e.g. edit_chat_message for corrections) and no explicit when-not guidance is given.

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