Plan Reference Replica

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

Annotations say readOnlyHint=false, destructiveHint=false, openWorldHint=true, and the description adds non-obvious state behavior: open_questions forces the plan to needs_input and blocks confirmation/generation, and edits invalidate prior confirmations. It also clarifies that frames are Agent-authored and that source copy is not auto-replicated. No contradiction with annotations.

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?

Purpose and the 'does not do' clause are front-loaded, then workflow, then state rules. It is dense and semicolon-packed, which suits a complex tool, but the volume is near the limit of comfortable scanning and could be split more cleanly across paragraphs.

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?

An output schema exists, so return values need not be described, yet the description still supplies the full lifecycle context: prerequisite inspection, analysis dimensions, source/target categories, state effects of open_questions, revision handling, and the export/confirm/submit handoff. Nothing an agent needs to call this correctly is missing.

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 reported as 0%, so the description must carry the load, and it does explain key semantics: brief.replica may be omitted in favour of the independent replica param, expected_revision controls edits, frames determine image count, facts must come from brief.facts, and SKU must bind to this version. It stops short of explaining design_id or every nested field, so not a full 5.

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 and resource: it saves the Agent's competitor decomposition, cross-category adaptation, and target frames, while explicitly stating what it does NOT do (recognize images, generate images). It names the sibling it defers to for new plans (build_reference_replica_prompts) and the export/confirm/submit chain, so an agent can tell it apart from neighbours without opening 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?

Gives explicit ordering and alternatives: prefer build_reference_replica_prompts for new plans, this tool is for legacy replica compatibility; first call inspect_design_images; for edits pass current expected_revision plus complete brief/replica. It even states the downstream sequence export_reference_replica → confirm_ecommerce_design → submit_ecommerce_design, leaving nothing to inference.

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