prepare_reply

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

Annotations already declare readOnlyHint=true, and the description adds useful behavioral details: it quotes the original message, replies from the account that received it, and does not send. These traits go beyond the annotation and help the agent understand expected side effects and flow. No contradictions with annotations.

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 two concise sentences, front-loaded with the primary purpose and followed by key behavioral notes and a pointer to commit_action. Every sentence carries meaningful information without wasted words.

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?

Given the presence of an output schema (so return values are covered), the description adequately covers the tool's core behavior: it prepares a reply, includes quoting and account selection, and explicitly states it does not send. While parameter details are not explained, the tool is a preparatory action and the description covers the essential workflow. Minor gaps like the effect of save_as_draft or reply_all remain but are secondary.

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%, yet the description does not explain any of the four parameters (body, message_id, reply_all, save_as_draft). It only implicitly references body via 'Quotes the original beneath your text' but does not clarify the meaning or interaction of reply_all and save_as_draft. The description fails to compensate for the missing schema documentation.

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 states a specific verb+resource: 'Prepare a reply to a message and return a preview for approval.' It clearly distinguishes from siblings (prepare_send, prepare_forward) by focusing on replies, including the quoting behavior and account selection. The final clause 'Does not send; use commit_action after the user approves' further clarifies its role as a preparatory step.

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 description provides clear context: it is for replying to a message, not sending. It explicitly directs the user to use commit_action after approval, indicating the follow-up step. However, it does not explicitly name alternative tools (e.g., prepare_send, prepare_forward) or state when not to use it, so it lacks explicit exclusions.

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