Create an article

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

The description adds substantial context beyond annotations: it always creates at draft status, the `status` field is rejected with a validation error, the operation mutates the customer's site, and it requires a secret key with articles:write scope. This goes well beyond the raw readOnlyHint/destructiveHint flags and gives the agent critical safety and behavioral information.

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 concise and front-loaded with the core purpose. Each sentence adds useful information: draft status, validation behavior, mutation, publishing separation, and auth requirements. It is slightly redundant in the opening ('Create an article' / 'Creates an article') but not padded, making it efficient and well-structured.

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 the tool's 16 parameters and absence of an output schema, the description covers the most important behavioral aspects: draft status, the impossibility of immediate publication, mutation of the site, and required authentication. It does not describe the response shape, but no output schema exists, and the core purpose and constraints are sufficiently clear for an AI agent.

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 covers 94% of parameters with descriptions like 'Send null to clear it,' so the schema already carries most parameter semantics. The description does not add parameter-specific details, but it does clarify that there is no field to make the article public, which is relevant to the `status` parameter. Baseline 3 is appropriate given high schema coverage.

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 clearly states the verb (create) and resource (article), and immediately specifies the key behavior: creates at `status: draft`. It distinguishes from siblings by noting that it cannot make content public and that publishing is separate, which sets it apart from publish_article and update_article.

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 gives clear context for when to use it: creating a new article that starts as a draft. It explicitly states a when-not ('publishing is always a separate call'), implying use another tool for publication. It does not explicitly name alternative tools for updates, but the draft-only behavior makes the boundary clear.

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