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

With no annotations, the description carries the burden, and it does disclose two non-obvious traits: this is non-sending, and it behaves as a patch (omitted fields keep prior values, "from" is ignored after creation). It does not say what is returned (presumably a draft id), whether the draft is validated, or where drafts surface, which keeps it at a 3 for an unannotated mutation tool.

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 short sentences, front-loaded with the core action, then the mode-selection rule, then the boundary against send_email. No filler.

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?

No output schema and no annotations, with seven optional parameters, so the description must supply the operational picture — and it does for creation, updating, and the no-send guarantee. It leaves the return value and the consequence of passing neither "from" nor draft_id unstated, a modest remaining 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 100%, so per-field descriptions already do the heavy lifting and a 3 is the baseline. The description adds cross-parameter semantics the schema cannot express: create-vs-update mode selection via "from" vs draft_id, and merge behavior for omitted fields. That is genuine added meaning.

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 concrete verb and resource ("Writes down a message being prepared") and immediately frames the lifecycle (start one with "from", rewrite one by its id). It also distinguishes itself from send_email, so an agent can place it among 65 siblings without opening the schema.

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?

Gives explicit when-to-use branches (pass "from" to create, pass draft_id to update) and an explicit when-not: "Saving sends nothing: send_email is what sends." The alternative tool is named with the condition that selects it.

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