update_draft

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

With no annotations, the description carries the full burden; it does disclose valuable behavior — that omitted headers, threading and attachments are preserved, and that [] vs None have different effects on attachments. It omits permissions/auth requirements, error behavior for a missing or already-sent draft, and whether the update is reversible.

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?

Short, front-loaded, and each sentence carries distinct information — purpose first, then per-field sentinel rules. The only blemish is the 'body is required' line, which is misleading rather than wasteful.

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 seven-parameter mutation tool with no annotations and no output schema, the description covers the non-obvious semantics (preservation, attachment clearing) that an agent would otherwise get wrong. Return values are unspecified and the body-required statement conflicts with the schema, leaving a small but real gap.

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 largely does: it defines the sentinel semantics for to/subject/cc/bcc (empty string retains) and attachments (None preserves, [] removes), which the bare schema defaults do not convey. The main gap is the claim that 'body is required' while the schema's required list contains only draft_id, and draft_id itself is never described.

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?

States a specific verb and resource ('Update a draft body') plus the preservation guarantee, which distinguishes it from create_draft and delete_draft. It stops short of explicitly naming those siblings, but the verb/resource pair is unambiguous.

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 explains how existing values are treated, which implicitly tells the agent this is the tool for partially editing an existing draft rather than creating one. It never states when to prefer it over create_draft or delete_draft, nor any precondition such as the draft existing or not yet being sent.

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