patch_object

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

Annotations already declare this is a non-read-only, closed-world mutation, and the description adds a real behavioral trait beyond that: nested objects replace rather than merge, which directly affects how a patch is authored. It omits other mutation-relevant context such as revision-conflict behavior (expectedRevision) and whether the change is undoable, keeping it below a 5.

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?

Two sentences with no filler: the patchable surface is front-loaded and the replace-semantics plus the read-first prerequisite follow in order of importance. Nothing repeats the name or title.

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 mutation tool with a free-form nested object payload, no output schema, and zero parameter documentation, the description covers the what and the replace semantics but not the payload contract or failure modes. An agent could call it only after doing the recommended describe_layer round-trip to learn the field structure.

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% across five parameters, and the description only gestures at the 'patch' payload via a list of field families, giving no shape, key naming, or nesting expectations. layerId, requestId, sessionId, and expectedRevision carry no explanation anywhere, and the concurrency contract of expectedRevision is left entirely 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 ('Patch') plus a resource ('Layer fields') and enumerates the patchable domains (text, typography, transforms, effects, masks, repeater, visibility, stroke, geometry, particle configuration), so the agent knows the scope precisely. It stops short of differentiating itself from the sibling 'update_layer' or 'edit_entity', which appear to overlap in intent.

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 one concrete prerequisite: 'read describe_layer first', which is genuinely useful sequencing guidance. It never says when to prefer patch_object over update_layer, edit_entity, or batch_actions, so the agent must infer the boundary between overlapping mutators.

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