Bulk delete messages

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

The description discloses the crucial two-step behavior (non-destructive first call with confirm_token, destructive second call) and the 14-day Discord limitation. This adds significant context beyond the destructiveHint=true annotation, clarifying that the first call is safe.

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 sentences long, front-loaded with the core action, then the constraint, then the safety workflow. Every sentence contributes essential information with no redundancy.

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?

The tool has 7 parameters, a destructive annotation, and no output schema, so the description carries a heavy burden. It covers the workflow and constraints well, but omits dry_run semantics and contains an inconsistency: it states '2 to 100' while the schema permits a count minimum of 1. This leaves a potentially confusing ambiguity.

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 description adds meaning to confirm_token (repeating the call with it deletes) and ties contains/from_author to filtering. However, dry_run is not explained, leaving a gap for that parameter. Schema covers most other fields, so the description adds partial value.

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 the tool deletes many recent messages at once (2 to 100), with optional filters by author or text. This specific verb+resource+scope distinguishes it from siblings like delete_message, which handles a single message.

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 two-step confirmation flow is explicitly described: first call returns the list and confirm_token, second call deletes. It also notes Discord's 14-day age limit, providing clear context. However, it does not explicitly contrast with delete_message or other alternatives, though the bulk-use case is implied.

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