create_project_from_preflight

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

With no annotations, the description carries the full behavioral disclosure burden and does so thoroughly: it declares the create as reversible, notes confirm_open_questions is ignored, explains legacy v1 blocking labels grant no execution authority, and constrains play_style so it cannot grant dispatch, live-action, production-write, or approval authority. This goes well beyond the basic side effect implied by the name.

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 a clear one-sentence purpose, and every subsequent sentence adds a distinct guardrail, compatibility note, or side-effect disclosure. It is somewhat dense and repeats the 'grants no authority' idea, but none of the content 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?

Given no annotations and no schema-level descriptions, the description provides sufficient detail to invoke the required parameters correctly and understand side effects, reversibility, and legacy behavior. The output schema covers return expectations, and the remaining gaps around workspace_id, idempotency_key, and repo_connection_id are secondary to the core flow.

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?

At 0% schema description coverage, the description compensates for most key parameters: receipt_json must be complete and unchanged, coding_harness is restricted to codex/claude_code/chatgpt, confirm_create must be the literal true, play_style is an optional bounded preference, and confirm_open_questions is an ignored compatibility argument. However, workspace_id, idempotency_key, and repo_connection_id are not explained, leaving a few parameters underdescribed.

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 verb ('Create') and resource ('exact project draft in a preflight receipt'), plus the required precondition 'after confirmation'. Distinguishes it from related siblings by emphasizing the exactness of the draft and the requirement to pass the preflight receipt unchanged.

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?

Explicitly instructs to pass the complete JSON from preflight_project_creation unchanged and specifies required values for coding_harness and confirm_create. It also states what is not accepted (no plan, inferred scope, approval state, or next-question answer) and routes review questions to the Project Agent, providing clear when/when-not guidance.

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