delete_messages

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

With no annotations, the description carries the full behavioral burden, and it discloses only the for-everyone-vs-local distinction. It omits critical traits for a destructive operation: irreversibility, time-window limits on for-everyone deletion, permission requirements, and side effects on other participants. The one behavioral fact it does supply is genuinely useful, keeping this above a 1.

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 with zero filler and the scope qualifier placed immediately after the verb. The parenthetical is slightly compressed to the point of ambiguity ("locally" is a loose way to say "only for you"), but no sentence is wasted.

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?

An output schema exists, so return values needn't be explained, but for a destructive three-parameter tool with no annotations and 0% schema coverage the description is thin. It should at minimum state that deletion is permanent, who may delete what, and what the chat and message_ids parameters accept. As written, an agent could call it correctly only by guessing at the required fields.

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 0%, so the description must compensate, and it only partially does. The parenthetical "your own for everyone, or locally" explains the semantics of the for_everyone boolean (and its default of true) better than the bare schema title. However, "chat" and "message_ids" get no format guidance (chat ID vs username vs link; how many IDs are allowed per call), leaving the two required parameters entirely to guesswork.

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 gives a specific verb and resource ("Delete messages") and adds a parenthetical scope note distinguishing own-message deletion for everyone from local deletion. No sibling tool overlaps meaningfully (leave_chat is about the chat, not messages), so the agent can identify the operation immediately. It stops short of stating prerequisites or scope constraints, which keeps it from a 5.

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?

There is no when-to-use guidance at all: nothing says whether this works on other people's messages, whether admin rights are needed, or how it relates to edit_message or leave_chat as alternatives. The only implied routing is that it deletes rather than posts, which the name already conveys. An agent must infer every usage condition.

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