Art direction before generating

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

With no annotations, the description carries the transparency burden and does disclose non-obvious behavior: quality defaults to premium, omitting overlayText changes the composition request, and very wide targetAspect values change the composition guidance. It does not state whether the call is read-only/side-effect free or whether guidance depends on a prior brand_profiles lookup, leaving a small gap.

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 most decision-critical instruction (call before generation) is front-loaded, and every sentence adds information with no filler. Slightly dense in the second half where context-population rules and the exactText caveat stack up, but nothing is expendable.

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 tool with deep nested objects, no annotations, and no output schema, the description covers what is returned and how to prime it well. It leaves unstated how `brand_id` and the inline `brand` object interact and what happens if project_profile is unavailable, which matters for a tool whose output quality hinges on that context.

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 only 33%, so more compensation was needed. The description adds real meaning for `context` (fill from project_profile and the conversation, exactText for every word) but says nothing about `asset_type` — the primary required enum with 13 values — or how `brand_id` relates to the nested `brand` object.

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 action and output: it returns designer-grade guidance (concept directions with ready prompts, critique checklist, iteration process) rather than the asset itself. It explicitly distinguishes itself from image_generate and video_generate by positioning as the pre-step, so an agent can route correctly without opening the schema.

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 ordering rule — 'Call this BEFORE image_generate or video_generate' — naming the alternative tools and the condition that triggers this one. It also tells the agent how to populate `context` from project_profile and the conversation, and calls out the exactText requirement for word-bearing asset types.

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