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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does a strong job: it discloses async behavior (poll it with get_blueprint_run), the return shape ({id, status, tokens_charged}), token costs (200 for product-ad), the GENERATIVE vs FFmpeg distinction, and the awaiting_review pause/resume flow for caption-video. It doesn't state rate limits, idempotency, or error behavior, but for a tool with no annotations this is well above average transparency.

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 long but earned: it front-loads the operation ('Start a blueprint run'), return shape, and polling/alternative hints before the per-blueprint field catalog. The catalog itself is dense and repetitive, but each line enumerates distinct parameters that the schema cannot express for a dynamic inputs object. It could be tightened (e.g., grouping multi-output notes), but every line carries information the agent needs.

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 15-blueprint polymorphic tool with an opaque generic input schema and no annotations, the description is near-complete: it covers per-blueprint required/optional fields, enums, token costs, the awaiting_review pause, polling/resume alternatives, and output expectations. It doesn't include an explicit example payload, and input URL format is only hinted by the types in the field descriptions, but no output schema exists and none is promised, so the coverage is strong.

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?

The input schema only describes inputs as an object and slug as a Blueprint to run, so the description must do the heavy lifting. It does: enums for slug, required fields per blueprint, enum options for style/position/fit/direction and output types, and the multi-output note for listing-kit and hook-variants. Subtraction: the input schema also has a 'viral-short' slug while the description says 'viral-short' — same, okay. There is a minor mismatch: the schema enum includes 'product-slideshow' while description says 'product-slideshow' with photo1_url.. photo3_url?..photo5_url? – okay. The description maps fields to each slug, which the schema's generic inputs object does not. This is genuinely additive.

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: 'Start a blueprint run — a pre-built video workflow.' It clearly distinguishes from siblings by listing the exact blueprint slugs and pointing to get_blueprint_run and run_blueprint_and_wait as alternatives. The distinction from take-this-instead tools like run_blueprint_and_wait is explicit.

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 provides explicit when-to-use guidance: it tells the agent to poll with get_blueprint_run, use run_blueprint_and_wait as a synchronous alternative, and mentions continue_blueprint_run for resuming. It also clearly states the required versus optional fields per blueprint and even flags which blueprints are generative vs FFmpeg-based, affecting token usage. This is comprehensive usage guidance.

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