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

With no annotations, the description carries the full burden and does so well: it discloses that a control token is returned and must be saved securely, explains idempotency key reuse for retries, and notes that optional fields raise listing completeness. It also implies the draft is private. These are critical behavioral traits for a submission 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?

Extremely concise: five short sentences. The most critical instruction (save the token securely) is front-loaded after the purpose. Every sentence earns its place by conveying essential operational details without fluff.

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 23-parameter creation tool with no output schema and no annotations, the description covers the essential workflow (create draft, save token, retry with idempotency key) and hints at optional field usage. It doesn't fully detail return values or all parameter semantics, but the schema covers most. It's largely complete for an agent to proceed, though a note on what the response contains beyond the token would help.

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 48%, so the description compensates by listing many optional fields (tagline, long_description, audience, etc.) and giving high-level guidance to write them in your own words from the website. However, it doesn't explain required fields (url, name, idempotency_key) or provide syntax for nested objects like links, screenshots, faq. Baseline 3 is appropriate given partial schema coverage and some added value.

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?

Clearly states the specific action and resource: 'Create a private project draft.' The 'private draft' scoping and 'No signup' distinguish it somewhat from siblings like update_submission or verify_submission, though it doesn't explicitly name them. A solid, clear verb+resource statement.

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?

Provides crucial context: 'No signup' lowers the barrier, and the token advice, idempotency retry guidance, and parameter advice imply when and how to use it. It doesn't explicitly say when to use this vs update_submission or what happens after creation, but the draft-oriented guidance is strong.

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