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

With no annotations, the description carries the safety burden and does well: it discloses the mandatory preview/confirm gate, the consent flag, and real side effects (clearing quoted references and related album items). It also states the honest caveat that recall does not guarantee the recipient hasn't read or saved the message. It stops short of stating irreversibility or how the timeout window is measured.

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 content is dense but front-loaded and every clause carries information — eligibility, procedure, side effects, caveat. The semicolon-chained telegraphic style is slightly cryptic and could be split into clearer steps, but there is 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?

For a five-parameter destructive tool with no annotations and no output schema, the description covers gating, the two-phase confirmation flow, side effects, and limitations. Only minor items are missing, such as what the preview payload contains and the length of the recall timeout window.

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 0%, so the description must compensate, and it explains the non-obvious semantics: preview defaults to a read-only preview, previewHash must be carried from that preview, consent must be true, and preview=false toggles the actual recall. conversationId is only alluded to via previewing the conversation, which is a minor gap given it is a required parameter.

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 opening clause states the operation precisely: recall only the caller's own messages that have not timed out, and it names read_messages as the source of messageId. This distinguishes it from neighboring message tools like send_message, delete_my_moment, or hide_live_message without needing 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?

It gives an explicit prerequisite (log in, obtain messageId via read_messages) and an explicit two-step procedure: call with defaults to preview the original text and conversation, then confirm with the same parameters plus previewHash, consent=true, preview=false. Eligibility limits (own messages only, no timeout exceeded) act as clear when-not conditions.

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