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

Adds real context beyond the annotations: omitted files carry forward unchanged, earlier versions are retained, and the call returns the new version plus a preview_url, plus a cost guarantee ("Cannot spend money"). The patch/versioning model reconciles well with idempotentHint=false and destructiveHint=false, though repeat-call behavior is left implicit.

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?

Four short sentences, each doing distinct work: what it does, how it merges, when to use it, and what comes back. Front-loaded with the action, no filler, though the closing cost line could be folded into the return sentence.

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?

With no output schema, the description usefully names the key return values (new version, preview_url) and covers mutation semantics and version retention. The only real gap is that the required `draft_id` and the `files` item shape are never explained.

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 description coverage is 0%, so the description must carry the parameter burden. It explains the patch semantics of `files` (send only what changes; omissions carry forward), which is genuinely valuable, but never clarifies `draft_id` or that each file entry has path and content, leaving the required array items undocumented.

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 ("Writes a new version of an existing draft") and makes the patch semantics explicit, which separates it in spirit from create_draft (new draft) and get_draft (read). It never names those siblings, so the differentiation is inferred rather than stated.

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?

"For when the user wants to change the copy, sections or layout of a draft that already exists" gives a clear triggering condition and implicitly excludes creation via "already exists." No explicit when-not or named alternative tool is given.

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