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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description adds value beyond those. It warns to 'Resolve and verify chat/message first', explains the uniqueness constraint (providers may only guarantee uniqueness inside a chat, so keep chat_id with message_id), and gives concrete sources for the IDs. It also explicitly lists 'Never pass' items, which prevents common errors. This is useful behavioral context beyond the 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 front-loaded with the core purpose ('Delete one exact message') and then gives a caution. However, it repeats the same 'Never pass' directives both in the main description and again inside the parameter descriptions, and the phrasing is somewhat redundant (e.g., 'Resolve and verify' and later 'In V2 always keep chat_id together'). While not excessively long, it could be tightened by removing duplicated guidance without losing substance.

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 3 parameters (2 required) and no output schema, the description provides thorough guidance: it explains how to obtain both IDs, the importance of pairing chat_id and message_id, and what not to pass. It also warns about the destructive nature. The only minor gap is that it does not describe the expected response (e.g., success/failure) or any post-deletion effects, but since there is no output schema and the task is straightforward, this is sufficient.

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%: the schema descriptions for chat_id and message_id already contain the full text about how to obtain them, the uniqueness note, and the 'Never pass' lists. The tool description essentially repeats this content, adding no new meaning beyond what the schema already provides. The account_id parameter is described only in the schema, and the description does not comment on it. Thus the description adds marginal value over the schema, so the baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Delete one exact message.' It clearly states the action and the target (a message), and emphasizes precision ('exact') which distinguishes it from fuzzy or batch deletes. The warning 'Resolve and verify chat/message first; destructive' reinforces the specific scope. While it doesn't compare itself to siblings, the unique action (delete vs. edit, forward, react) is 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?

The description gives clear context: you delete a message after resolving and verifying the chat and message IDs, and it warns that deletion is destructive. It provides explicit instructions on how to obtain the correct IDs (via list conversations and read messages) and what not to pass. However, it does not explicitly name alternative tools or describe when not to use this tool (e.g., when you might want to edit rather than delete). The guidance is strong for execution but lacks explicit rutting vs. siblings.

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