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

Annotations only give destructive=true, idempotent=false, openWorld=false. The description adds real behavioral context beyond that: single atomic write, unsetProps runs before other patches, propsPatch deep-merges objects while strings/arrays replace, nodesPatch is reorder-only and blanks the canvas otherwise, image nodes reject content writes, and validation-mode defaults.

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-loads the scope and the alternative in the first clause, then uses semicolon-dense fragments to pack merge/unset/image semantics. Every clause carries information, though the compressed telegraphic style slightly hurts readability.

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 an 11-parameter destructive mutation with no output schema, the description covers the dangerous cases (reorder blanking canvas, image content rejection, patch ordering) well. Minor gaps remain, e.g. what the write returns and whether the site id/name fields interact with the node patch, but nothing essential 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 coverage is 100% (baseline 3), but the description goes well beyond it: twMerge class merging, deep-merge vs replace semantics for propsPatch, ordering of unsetProps, and the image src-only/content-rejection constraint. That is genuine added meaning, not restatement.

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 (patch one node) and immediately distinguishes itself from the batch sibling patch_site_bulk by noting the single-node, atomic-write scope. An agent can tell it apart from add_nodes/insert_node/move_node without opening another 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?

Explicitly routes multi-node edits to patch_site_bulk and points to get_style_reference({ topic: "editing" }) for rules, which is strong context. It stops short of saying when to prefer patch_site_node over insert_node/move_node for structural changes, so it is clear but not fully exhaustive.

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