draft_update

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

With no annotations, the description carries the full burden and discloses critical behavioral traits: it is implemented as delete-and-recreate, the returned draft_id is new, and the original id becomes stale. It also states the patch semantics (None=keep, empty=clear) and that it does NOT send. This is thorough and goes well beyond any structured metadata.

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 efficiently written—three short paragraphs, each serving a distinct purpose: stating the action, defining patch semantics, and alerting about the destructive implementation. It is front-loaded with the core message and every sentence adds value without redundancy.

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?

Despite the tool's complexity (10 parameters, nuanced behavior), the description covers all essential aspects an agent needs: the operation, the patch semantics, the send alternative, and the critical side effect of a new draft_id. The presence of an output schema handles return-value details, so nothing critical 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?

The description provides a universal semantic for all optional parameters: 'only fields you pass change. None means keep existing; empty list/string means clear.' This compensates for the 50% schema description coverage and gives clear meaning to fields like template_name and template_vars that lack schema descriptions. The explicit attachment override behavior (None=keep, []=clear, list=replace) is also reflected.

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 precise verb and resource: 'Update an existing draft' and immediately clarifies the scope with 'DOES NOT SEND.' This cleanly distinguishes it from sibling tools like draft_send and draft_create, leaving no ambiguity about what the tool does.

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 tells the agent when to use this tool versus alternatives: it is for updating drafts, not sending. It even points to draft_send(draft_id) as the follow-up call, giving a clear context for use and excluding the sending scenario. The delete-and-recreate note also signals when this tool is necessary despite its side effects.

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