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

Annotations only declare the generic profile (readOnly=false, idempotent=true, destructive=false, openWorld=false). The description adds material behavior the annotations cannot: on already-published pages the edit writes only an unpublished latest revision, leaving the live page untouched, and it imposes a turn-boundary workflow constraint that prevents an agent from chaining a publish immediately after the edit.

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?

Front-loaded with the action and the field scope, then the workflow guardrails. Slightly long: the publish/unpublish prohibition is restated across three sentences (do not publish this turn, wait for an explicit request, do not unpublish either) where two would carry the same meaning, but each sentence still maps to a distinct failure mode.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining risk areas for a mutation tool: partial-patch semantics, the draft-vs-live consequence for published pages, and the sibling tools that must not be chained. Nothing an agent needs to call this correctly is missing.

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 only 33%, so the description must carry weight; it names the enum-constrained field groups but does not explain the non-enum surface (the background oneOf branches for solid/gradient/image, or text_color/accent_color/muted_text_color). Since the nested schema properties do carry their own descriptions and enums, this is adequate but not compensating for the low coverage figure.

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+resource ("Apply a partial theme patch") and immediately scopes it by enumerating the enum-constrained theme groups it touches (button variant/radius/shadow, font family/weight, density, icon_size). This distinguishes it from sibling mutators like page_header_update and page_meta_update, which patch different regions of the page.

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 alternative for a related intent ("Use presets_list first if the user wants a complete restyle") and two hard exclusions with their triggering conditions (do not call page_publish in the same turn; do not call page_unpublish unless the user explicitly asks to take the page down). It also prescribes the exact next step after the edit — stop and report the draft update, then wait for an explicit user request.

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