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

Annotations declare destructiveHint=true and idempotentHint=true, and the description backs those with concrete behavior: atomic application, 'Reuse the SAME request_id after a lost response', and 'A revision conflict requires rereading; never force overwrite'. It further discloses the blast radius ('edits the draft only', 'remove nodes only when requested') and the post-mutation verification loop, well beyond what the annotations state.

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?

The trigger condition is front-loaded and nearly every sentence is actionable (conflict handling, request_id reuse, post-apply verification, frame sizing rules). It is dense but the back half runs long as a string of imperative clauses, which slightly hurts scanability.

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 destructive, revision-guarded bulk mutation with no output schema, the description covers prerequisites, concurrency semantics, idempotent retry, draft-vs-generation scope, and the response signal to act on ('if layout_warnings are returned, fix them'). An agent has enough to invoke it correctly and resolve conflicts.

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 0%, so the description must carry the load; it does explain the intent behind expected_rev (revision-conflict handling) and request_id (idempotent retry). However, the operations array is an unconstrained object list and the description only hints at operation kinds ('layout_composition', 'add_note', exact node IDs, w/wrap) without conveying the operation object shape, leaving the most important parameter underspecified.

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 ('applies semantic edits, including server-planned layout_composition, atomically') on a specific resource ('your Canvas project at expected_rev'). It also scopes the tool away from generation ('This edits the draft only; generation uses the existing quote/submit tools'), so an agent can separate it from sibling execution tools without reading schemas.

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?

Opens with an explicit trigger ('Use when the user asks to add or edit text, titles, frames, layout or nodes'), names a prerequisite ('Read capabilities and the project first'), and routes excluded work elsewhere ('generation uses the existing quote/submit tools'). It even prescribes the follow-up tool by name ('call aimixer_canvas_inspect_layout').

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