Apply Excalidraw canvas changes

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

With no annotations, the description carries the full burden. It does disclose two real behavioral traits: atomicity (all-or-nothing application) and the base-revision requirement, which implies the call will not blindly overwrite newer state. However, it does not disclose conflict behavior on stale revisions, whether this is a destructive write, or how failures surface. 'Atomically' also misleadingly implies the description is complete when it is not.

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?

A single dense sentence with zero filler. The verb and the atomicity constraint are front-loaded, and the base-revision qualifier earns its place by explaining the concurrency contract. This is appropriately sized for what it attempts to convey.

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?

This is one of the most complex tools in the set (5 required params, an 11-op changes union, 200-item batches, no output schema, no annotations), yet the description is a single sentence. It omits how to construct changes (e.g., from inspect_canvas), the meaning of clientRefs, what happens on a revision mismatch, and the return/conflict behavior. The agent is left to infer critical operational details.

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 40%, so the description must compensate. It partially does: 'element and canvas changes' maps to the changes parameter, and 'at one base revision' explains baseRevision's purpose. But mutationId's role (e.g., idempotency/deduplication) is never explained, and the clientRef-vs-elementId referencing model that pervades the changes schema is absent. The description adds a little meaning but leaves most parameter semantics to the schema.

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?

The description states a specific verb ('applies'), a clear resource ('semantic element and canvas changes'), and a defining constraint ('atomically... at one base revision'). This communicates a batch-commit operation with optimistic concurrency semantics. However, it does not explicitly distinguish itself from siblings like push_canvas, replace_canvas, or save_canvas_copy, which an agent may confuse it with.

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?

No guidance is provided on when to use this tool versus alternatives such as push_canvas (full-state commit) or replace_canvas. The 'at one base revision' phrase implies a concurrency-aware workflow, but no explicit when-to-use, prerequisites, or exclusions are stated. For a tool with 24 siblings, this is a significant gap.

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