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

Annotations already declare readOnlyHint=false and idempotentHint=true, but the description adds mechanism the annotations do not: compare-and-swap via expected_rev and idempotency keyed by request_id, plus the guarantee that edges and node ID are preserved. It omits what happens on a revision conflict or a duplicate request_id, so the picture is not complete.

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 compact sentences, both front-loaded: the core action and node-type scope come first, followed by the in-place/no-recreate guarantee. No filler or repetition.

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 five required params, deep nesting, and no output schema, the description leaves too much unsaid: the shape and semantics of patch, the failure behavior on stale expected_rev, and what a successful patch returns. Safety hints are covered by annotations, but the operational contract an agent needs to call this correctly is largely absent.

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 required parameters, including a nested patch object with content/geometry/generation sub-objects. The description only carries real meaning for two of them (request_id as idempotency key, expected_rev via CAS) and never explains what patch fields are accepted or what project_id/node_id scoping means, leaving the most complex parameter 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?

Names a specific verb (patch) and resource (node) and scopes it to NOTE/TEXT/idle generation nodes, which lets an agent tell it apart from canvas_delete, canvas_read_node and canvas_create. It stops short of naming an alternative sibling explicitly, but the 'never delete/recreate' constraint does most of the differentiation work.

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?

'Patch an existing ... node in place' and 'never delete/recreate' imply when to reach for this tool rather than recreating a node, but there are no explicit when-to-use/when-not conditions, no prerequisites, and no named alternative such as canvas_apply or canvas_delete. Usage is inferable rather than stated.

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