update_draft

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

The description discloses partial update behavior ('Only provided fields are updated — omitted fields retain their current values'), which is valuable. However, it misleadingly instructs to call sync_draft_to_remote after updating, contradicting the syncToRemote parameter that defaults to true and auto-syncs when IMAP is available. This creates confusion about whether the tool syncs automatically. Annotations only provide destructiveHint: false, offering minimal safety context, so the description carries the transparency burden and partially fails.

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 purpose, no filler. Every sentence contributes to understanding the tool's function, usage, or next steps. The structure is 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?

The description covers purpose, usage, partial update behavior, and follow-up actions, but the sync guidance is misleading and omits the existence of the syncToRemote parameter behavior. Given the tool has 12 parameters and no output schema, this is a notable gap that could cause incorrect invocation. It is adequate but not fully reliable.

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 92%, so the baseline is 3. The description adds meaningful parameter behavior beyond the schema by explaining that omitted fields retain their current values — a critical semantic that is not apparent from individual field descriptions. It also clarifies the draftId refers to a 'locally saved draft.'

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 opens with a clear, specific verb and resource: 'Update an existing locally saved draft's recipients, subject, body, or other fields.' This distinguishes it from create_draft (creates new), send_draft (sends), and sync_draft_to_remote (syncs). The partial update semantics further clarify the tool's scope.

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 explicitly states when to use it ('Use to edit a draft before sending') and provides alternatives for subsequent actions ('call send_draft to send or sync_draft_to_remote to push to Proton Drafts'). This clearly separates it from sibling tools.

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