apply_transform

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

Beyond the annotations, the description discloses meaningful behavioral traits: idempotent behavior with existing derived revisions, preset-to-recipe hash equivalence, ICC color profile dropping for certain encode formats, and warning-as-not-error semantics. It also clarifies that a new revision is issued. This goes well beyond what readOnlyHint, destructiveHint, and idempotentHint already communicate.

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 description is packed with essential information but remains well-structured and front-loaded with the core purpose. Each sentence contributes unique value: input constraints, sibling tool pointers, idempotence, and an edge-case warning. No filler is present.

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 complex transform tool, the description covers input selection, mutual exclusivity, batch behavior, idempotence, encoding caveats, and where to find operation catalog details. An output schema exists, so return-value details need not be duplicated. The description is complete enough for an agent to call the tool correctly in both single and batch scenarios.

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?

Even though schema description coverage is 100%, the description adds critical parameter semantics not encoded in the schema: recipe structure with operations applied in order, at most one encode operation and it must be last, the exact one-of relationship, batch size limit of 64, and per-item failure isolation. The note about ICC profile behavior further clarifies the recipe parameter's practical effects.

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 begins with a specific verb and resource: 'Apply a transform recipe at full resolution and issue a new revision.' It clearly distinguishes this from siblings like render_preview and export_asset by emphasizing full-resolution processing and revision creation. The operation's core input alternatives are also stated, leaving no ambiguity about what the tool does.

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?

The description gives explicit usage context: exactly one of recipe/preset and exactly one of revision_id/revision_ids, plus batch limits and failure semantics. It also points to sibling tools list_operations and explain_operation for prerequisite knowledge. However, it does not explicitly state when not to use this tool versus siblings like render_preview, so it stops short of a full 5.

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