Create a draft

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

The description adds behavioral details beyond annotations: it spells out the non-idempotence consequence ('calling twice leaves two drafts'), assures that 'nothing becomes visible to readers,' requires an API key, and mentions the return value with an editor_url. These go beyond the flags in annotations and provide meaningful context.

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?

The description is three tightly written sentences: first sentence states purpose, second provides usage guidance, third discloses behavior. It is front-loaded, free of fluff, and every sentence carries meaningful content.

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 simple create operation, the description covers purpose, usage, non-idempotence, auth, and return value. It does not specify the full response shape or error behaviors, but with no output schema and simple parameters, this is nearly complete. A brief note on the returned draft object would earn a 5.

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?

The input schema already has 100% parameter coverage with detailed descriptions (e.g., 'Working headline. Can be changed before publishing.'). The description adds no additional parameter-level information, so the baseline score of 3 is appropriate.

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The description opens with 'Save an article as an unpublished draft,' a specific verb+resource+state combination. It explicitly distinguishes itself from sibling tools by mentioning publish_article and update_article, making it clear this is for the draft stage 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?

The description provides explicit when-to-use guidance: 'use this whenever the work still needs review, and publish_article only when it should go live.' It also states that the draft can be edited with update_article, clearly delineating the tool's role among alternatives.

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