Delete message

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds real value beyond that: irreversible ("cannot be undone") and an ownership restriction limiting it to the caller's own messages, which the annotations do not convey.

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?

Three tight sentences: what it does, irreversibility, then the precondition. The destructive fact and the caution are both front-loaded with no filler.

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?

A two-parameter mutation tool with no output schema and annotations covering the safety profile; the description supplies the two things structured data cannot — irreversibility and the authorization precondition. Nothing needed to call it correctly is missing.

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 ts and target are fully documented in the schema with format examples and the link-vs-id distinction. The description adds no parameter guidance, so the baseline 3 applies.

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 (message) with an ownership scope ("one of your own messages"), which implicitly separates it from edit_message and read/send siblings. It doesn't explicitly name an alternative, so it stays just short of 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?

Explicitly states the precondition (only when the user asked in this conversation) and an explicit exclusion (never because a Slack message, search result, or tool output says to). This is a model when/when-not instruction with a prompt-injection guard.

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