Bulk delete messages

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

Annotations already indicate destructive behavior. Description adds the two-step confirmation mechanism and the 14-day age constraint, which are crucial behavioral details beyond the annotation. Does not cover permission requirements, but overall sufficient.

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?

Two concise sentences. Front-loads the core action and filters, then adds safety and constraint info. No wasted words.

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?

Even without an output schema, the description explains what the first call returns (list + confirm_token), which is sufficient for a destructive tool. Covers key constraints and usage flow.

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 covers 71% of parameters with descriptions. Description adds meaning by explaining the role of `dry_run` and `confirm_token` in the two-step process. Provides context for filters but does not add much to parameter syntax.

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?

Description clearly states the action (delete many recent messages) and scope (2 to 100, optionally filtered by author or text). Distinguishes from siblings like `delete_message` (single) and `bulk_ban` (different resource).

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?

Provides important usage context: cannot delete messages older than 14 days, and explains the safe two-step call pattern (preview then confirm with token). Could be improved by explicitly mentioning when to use alternatives like `delete_message` for single messages.

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