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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context beyond the annotations: the mutation lands in a 'draft version' rather than the live site, the return value is a preview URL, and screenshot_page is the follow-up for visual verification. It stops short of saying whether existing draft edits are overwritten.

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?

Five tight sentences, each earning its place: action, when-to-use, path format, return value, and follow-up tool. The core operation is front-loaded before the routing and format details. 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?

With no output schema, the description correctly covers the return value ('Returns the preview URL') and the follow-up verification path. It also handles the path-format subtleties of JSON Pointer. It omits the 200-op limit and whether the prior draft is replaced, which are minor gaps for a two-parameter tool.

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 50% and the description's path-format note ('/theme/config/colors/primary', '/pages/0/tree/children/2') largely duplicates the example already present in the json_patch schema description, though the theme-token example is new. site_id remains undocumented in both places, albeit self-evident as a UUID. The description adds only marginal meaning over the schema, so baseline 3 is right.

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 — 'Apply an RFC 6902 JSON Patch ... to the latest fixture snapshot for a site, then save the result as a draft version.' It clearly conveys the operation and its output state. It implicitly contrasts with update_site_from_fixture ('without shipping the full fixture again') but never names a sibling tool, so it falls short of full differentiation.

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 an explicit when-to-use condition: 'Use this when you need precise multi-field edits across the fixture ... without shipping the full fixture again.' That is a clear routing rule. However, it offers no when-not guidance and does not name alternatives (e.g. patch_nodes, update_site_from_fixture) that an agent might otherwise confuse it with.

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