Publish an article

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

Beyond the annotations, it discloses the real-world impact: 'publicly visible on the customer's own live site, where search engines and readers will see it' and the confirm parameter's dry-run behavior. It also states the required secret key scope, adding meaningful context about auth.

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?

Every sentence carries essential information: the action, the immediate effect, the public visibility warning, the user-confirmation requirement, and the auth scope. It is front-loaded with the main verb and efficiently expanded.

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?

The description covers purpose, effect, safety confirmation, auth prerequisites, and the dry-run behavior, making it self-contained. Given the simple 2-param schema and no output schema, this is fully complete for an agent to invoke correctly.

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 schema already provides full coverage for id and confirm. The description adds extra meaning by explaining that omitting confirm 'returns a description of what would happen and changes nothing', which clarifies the parameter's gatekeeping role.

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 'Publish an article' and immediately specifies 'Makes the article public immediately, at `status: published`', giving a specific verb, resource, and outcome. This clearly distinguishes it from siblings like unpublish_article and schedule_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?

It states when to use (for immediate public visibility) and provides a critical safety guideline: 'Ask the user before calling this, and pass confirm: true only once they have agreed.' However, it does not explicitly mention alternatives like schedule_article for delayed publishing.

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