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

Annotations already declare destructiveHint=true, but the description adds substantial context the annotations cannot: the deletion is local-history only (recipient retains the message), it cannot undo a send, and it is irreversible with no restore tool. This is exactly the behavioral information an agent needs before invoking a destructive write.

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 sentences, front-loaded with what the tool does, then the critical scope caveat, then the safety instruction. Every sentence carries distinct information (scope, recipient impact, irreversibility, confirmation requirement) with no repetition of the name or title.

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?

Complete for a single-parameter destructive tool with full annotation coverage and no output schema. The description covers scope, side effects, reversibility, and the required human-confirmation step, so nothing an agent needs to call it safely 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 description coverage is 100% and the single messageId parameter is documented with its source (conversation_get or message_list), so the schema does the heavy lifting. The description adds no additional parameter-level guidance, which is the correct baseline for a fully documented single-param schema.

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 and resource ('Remove a message from the stored thread record') and immediately distinguishes the operation from the sibling action it is most likely to be confused with (message_send): it does not unsend anything and only edits the caller's own history. An agent can tell exactly what this tool does without opening the schema.

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?

Gives a clear precondition: show the user which message and obtain an explicit yes before calling, because the action is irreversible and no restore tool exists. It does not name a specific alternative sibling for the 'I want to unsend' case, only states none exists, so it falls just short of explicit when/when-not/alternatives routing.

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