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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description need not re-establish safety. It adds real context: the UI behavior (picks shown first, all other recipes still reachable a tap away), the presence of slugs in the result for start_recipe, and the credit-cost nuance for recipes marked `usesGeneration`. It does not describe failure modes or the exact result payload, keeping it short of a 5.

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?

It is front-loaded with the core purpose, then parameter guidance, which is the right order. However, the first two sentences are long and contain redundancy ('the answer when they ask what Cardboard can make or do' repeats the prior clause; the recipe explanation is convoluted), and the guidance on docs-vs-parameterless-call is slightly tangled. It is dense and mostly earns its space, but could be trimmed noticeably.

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 five-parameter read tool with no output schema, the description covers when to call, how to populate each parameter, the two-step flow with the `recipes` docs topic, and the display behavior of the card. It stops short of fully specifying the return payload beyond 'names the matching recipes with their slugs', which is the main remaining gap.

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?

With 100% schema description coverage, the baseline is 3; the description earns above that by clarifying what qualifies for `picks` ('only the recipes that make that whole kind of video... an effect, a title or a caption style is not a whole video'), that `also` is for alternative-kind recipes suited to the same footage, and that `search` is semantic rather than keyword matching. It does not add much on `heading` beyond the schema example, but overall adds meaning.

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 states a specific verb and resource — it shows Cardboard's recipe library as a card in the chat — and explains what a recipe is (a team-made edit template applied to the person's footage). It also distinguishes itself from read_recipe and start_recipe by noting the result lists slugs 'for start_recipe' and by pointing to the docs topic `recipes` for the full list.

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?

It gives explicit when-to-use rules: call it when the person asks what Cardboard can make, and when they have stated a goal, first read the docs topic `recipes` and then pass `picks`. It also gives a when-not rule for `search` ('for words the person asked to search for, not for finding what fits their idea') and a fallback ('call show_recipes without them first if you do not yet know the slugs').

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