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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial context beyond them: what is affected (received and sent messages), the recovery path (moved to Trash, restorable individually within seven days), and the terminal state (permanent deletion afterward). This tells the agent both the blast radius and the reversibility window.

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 sentences, no filler. The action and the human-confirmation requirement are front-loaded, with the recovery/irreversibility detail following. Every clause earns its place.

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 single-parameter destructive tool with destructive annotations and an output schema (which handles return values), the description covers scope, precondition, and lifetime of the deletion. Nothing an agent needs to invoke 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 description coverage is 0% for the single thread_id parameter, so the description carries the burden. It only implicitly maps 'conversation' to the thread_id and adds no detail on format or how to obtain the value, while the schema itself supplies type, uuid format, pattern, and required status. Baseline-level compensation, not more.

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 (every message in a conversation), and explicitly scopes it to 'received and sent', which distinguishes it from the sibling tools delete_message and delete_sent_message. An agent can identify the operation and its breadth 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 for use: confirm the conversation and its full scope with the human first, which is meaningful guidance for a destructive bulk operation. It does not, however, name alternatives (e.g. delete_message for a single message, restore_message for undo) or state when not to use it, so it falls short of the explicit routing a 5 requires.

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