Update a draft (deep-merge patch, or replace the config) — returns an inline preview image

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

With only openWorldHint=false in annotations, the description carries the full behavioral disclosure burden and does so well: it reveals deep-merge semantics (objects merge, arrays replace, null clears), wholesale replacement behavior for config and data, the non-publishing default, and the optimistic-concurrency conflict behavior. It does not mention authentication, reversibility, or what the preview image actually contains, but the core mutation semantics and side effects are transparent.

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 dense but every sentence carries operational meaning; there is no filler. It is front-loaded with the most important distinction (deep-merge vs replace) and the publish caveat appears at the end. It could be more scannable as a short bulleted list given the number of distinct rules, but the prose is efficient and well-ordered.

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 9-parameter mutation tool with no output schema, the description is largely complete: it covers merge vs replace, key removal, data replacement, concurrency, and publishing. The title promises an inline preview image but the description does not specify the full return envelope after success, nor does it discuss what happens to unmentioned fields when config replaces the whole config. However, the information needed to call the tool correctly is present.

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 56%, so the description must compensate for uncovered parameterscars — and it does. It adds critical semantics beyond the schema: configPatch deep-merges, config replaces and removes keys, data replaces rows wholesale, expectedVersion is required for conflict handling, and publish controls same-call publishing. Simple parameters like brand, title, and showcase have minimal schema info and are not elaborated, but the high-risk parameters are thoroughly explained.

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 title and description state a specific operation — updating a draft asset — with explicit modes: deep-merge patch via configPatch, wholesale config replacement via config, and data replacement via data. It also clearly differentiates from sibling publish_asset by stating that updating does not publish by default, and from get_asset by noting it returns a preview image. An agent can tell exactly what action this tool performs and how it differs from nearby write operations.

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 gives concrete when-to-use guidance: use configPatch for surgical updates, use config to remove keys or replace the whole config, get the current config from get_asset before editing, and pass publish:true or call publish_asset separately to publish. It also explains the expectedVersion/409 flow with re-merging onto returned current. This is explicit routing away from alternatives and clear operation sequencing.

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