Plan ad variations

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

Annotations are all false (readOnlyHint, idempotentHint, destructiveHint all unset), so the description carries the full behavioral burden. It discloses the key trait beyond annotations: it is planning-only and renders nothing itself, which prevents an agent from expecting visual output. It also clarifies that distinct hooks/mechanics/audiences are produced. No contradiction with annotations; readOnlyHint=false is consistent with this being a plan-generating (not necessarily side-effect-free) operation.

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?

Two compact sentences with the primary purpose front-loaded. The pipeline to generate_image and score_ad is conveyed efficiently via the dash. Minor redundancy exists ('LLM planning only' and 'renders nothing itself' restate the same point), but there is no wasted verbiage overall.

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 planning tool with no output schema and uninformative (all-false) annotations, the description provides solid operational context: what it produces (distinct angles, hooks/mechanics/audiences, headlines, visual briefs) and how it fits the downstream pipeline. The main gap is that it never describes the return structure, which would be valuable absent an output schema, but the workflow context is otherwise sufficient for correct invocation.

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 100% — all four parameters (brand, count, product, language) are already documented in the schema with their defaults and constraints. The description adds no parameter-level meaning, which is acceptable because the schema does the heavy lifting. Baseline 3 applies since the structured fields fully cover parameter semantics.

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 uses a specific, vivid verb ('Fan a brief into N DISTINCT ad angles') and names the resource and output artifacts (headlines + visual briefs). It differentiates itself from siblings by explicitly chaining to generate_image and score_ad and by stating 'LLM planning only; renders nothing itself,' which disambiguates it from render_ad and generate_image. An agent can distinguish this from plan_ad and mine_angles 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?

The description clearly implies usage — produce multiple ad-angle candidates from a brief, then hand each to generate_image and score_ad. The 'LLM planning only' clause sets a boundary for when this is the right tool (planning stage, not rendering). However, it does not explicitly name alternatives such as plan_ad or mine_angles, nor state when to prefer them, so exclusions are left implicit rather than stated.

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