创建官网项目

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

The annotations already declare idempotentHint=true and openWorldHint=true, and the description restates the idempotency contract in concrete terms (same operation_id plus same input returns the existing real receipt), which is genuinely useful for retry behavior. However, it says nothing about what the create operation actually materialises, what permissions or auth are required, or what happens if operation_id is reused with different input — the most important edge case for this contract.

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?

Two compact clauses, with the core purpose front-loaded and the idempotency constraint second. No filler, though the semicolon-joined phrasing is dense and could be split for readability.

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?

An output schema exists, so return values need not be explained, and the idempotency contract is covered. But for a three-parameter write tool with zero schema coverage, the description omits auth prerequisites, behaviour on conflicting input with a reused operation_id, and what a 'project' means in this product versus the script-project siblings.

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 0%, so the description must carry parameter meaning. It does add real semantics for operation_id (must be stable, acts as an idempotency key), but title and cover_url are left entirely undefined, including whether title must be unique or what cover_url expects.

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 pairs a clear verb (创建) with a clear resource (新项目), so an agent knows this is the project-creation tool. It does not differentiate itself from nearby creation tools such as pavo_script_create_ai or pavo_apply_template, and it drops the '官网' (official website) qualifier present in the title, so scope is slightly narrower than stated.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named despite many sibling creation tools. The only guidance-like content is the operation_id stability rule, which describes correct invocation rather than when to pick this tool.

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