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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds real behavior beyond that: it creates a project, populates specific paths, and triggers a UI side effect (opening upload_media's card). It does not state that repeated calls create separate projects or what happens on an invalid recipe, which matters for a non-idempotent tool.

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?

Front-loaded with the core action and outcome, then conditions, then parameter nuance. The single long compound sentence packs several ideas and takes effort to parse, but no sentence is filler.

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?

No output schema exists, and the description partially compensates by saying the result names still-open questions and that the upload card opens. For a 5-parameter creation tool it leaves gaps on error behavior, project identity in the response, and re-invocation semantics, but the essential mental model is present.

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 coverage is 100%, so the baseline is 3, and the description adds meaning beyond the schema for `answers`: answers are supplied "by id, as far as they have given them" and the result names the questions still open, clarifying that a partial answer set is legitimate. The `upload` and `recipe` semantics are essentially restated from the schema.

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?

Names a specific verb and resource ("Makes a new project from one of Cardboard's recipes") and enumerates exactly what is materialized: the recipe's brief, graphics and data in recipe/, its media, and answers in recipe/inputs.json. That detail separates it cleanly from siblings like create_project (blank project) and read_recipe (inspection only).

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 clear conditional guidance on the main branch point: when the recipe takes media, the upload card opens unless `upload` is false, and it explains how to obtain the recipe identifier ("slug from show_recipes"). It gives no explicit when-not or failure guidance (e.g. don't call on an unknown slug, don't call twice for the same project), so it stops short of full routing guidance.

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