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

Annotations declare destructiveHint=true and idempotentHint=true; the description adds real value on top by disclosing the two-phase preview/apply protocol, that the target node must be empty, that confirmation must come from the user, and that the call never generates or debits coins. It does not say whether an applied attach can be undone or what happens if the node becomes non-empty between phases — minor gaps given the annotation coverage.

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 core purpose and the sibling distinction in the first sentence, then packs the workflow into one long but tightly ordered second sentence. Dense but nearly every clause carries a constraint; only the parenthetical could be trimmed.

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?

With an output schema present, return values need no explanation; the description covers the safe mutation workflow, prerequisites, and the cost-free guarantee. For a 10-parameter mutating tool this is enough for an agent to invoke it correctly.

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 carries the burden: it conveys the meaning of phase (preview/apply), confirm (explicit confirmation), node_id (must be empty), project_id, generation_request_id, request_id, expected_rev and preview_proof (must match across preview and apply). However, it leaves expected_kind and output_index entirely undifferentiated and never explains the 64-hex proof format, so compensation is partial.

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 (insert/attach) and resource (a completed owned generation output) into a precise target (an empty Canvas media node). It also explicitly distinguishes itself from the closest sibling, aimixer_canvas_import_attachment, which handles attached files.

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 an explicit when-to-use rule (already FINISHED generation result), names the alternative for the other case, and states the precondition sequence (add placeholder first, preview, show effects, then apply only with explicit confirmation). Exclusions and ordering are both covered.

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