create_thread_reply_draft

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

No annotations provided, so description carries full burden. It discloses automatic selection of latest inbound message, mentions syncBefore (refresh IMAP index) and syncToRemote (sync to Proton Drafts). While it doesn't detail error cases or permissions, it gives sufficient operational context for a create operation. A minor gap: no mention of what happens if no inbound message exists.

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 packed with essential information: action, usage context, alternative, and return value. No filler or redundancy. Front-loaded with the core action, then guidance, then outcome. Highly efficient.

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 11 parameters, no output schema, and no annotations, the description covers the key behavioral scenario well. It explains the primary use case, the auto-selection logic, and the return of a draftId. Missing details about response structure beyond draftId, but the tool is part of a consistent draft workflow where return format is likely standard. Could mention that body is prepended to the reply, but it's implied.

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 descriptions cover all 11 parameters (100% coverage), so baseline is 3. The description adds value by explaining the overarching behavior ('automatically selecting the latest inbound message to reply to'), which clarifies why preferLatestInbound exists and its default true. It also explains the purpose of syncBefore in context, adding behavioral meaning beyond parameter names.

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 clearly states the tool creates a reply draft from a threadId, automatically selecting the latest inbound message. It distinguishes itself from create_reply_draft by specifying the different input (threadId vs emailId). Also mentions the return value (draftId) for later update or send, making the purpose very specific and actionable.

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 guides when to use: 'Use when you have a threadId from get_threads or get_actionable_threads'. Directly contrasts with sibling: 'Prefer create_reply_draft when you already have a specific emailId'. This provides clear decision criteria for the agent.

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