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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description reveals important behavioral details: the artifact is empty, owned by the current principal, visibility defaults to private, comments default to signed-in users, and no source version is published. These are meaningful behaviors not captured in the annotations, expanding the agent's understanding of side effects and defaults. It doesn't cover every possible side effect, but adds substantial 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 sentences with no redundancy: the first states the core action, the second conveys defaults and versioning state, and the third gives a direct next-step tip. Every sentence earns its place, and the most important information (creation and empty state) is front-loaded.

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 moderate complexity, complete schema coverage, annotations, and an output schema, the description covers all critical aspects: what is created, ownership, defaults, and the un-published state. It also points to the next logical operation. It could have added a note about content input restrictions, but that is not necessary for basic usage and would likely be in the output schema.

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 100%, so the schema already fully describes all parameters, including defaults and idempotencyKey semantics. The description reinforces that visibility defaults to private and comments to signed-in users, but adds little beyond the schema definitions. This matches the baseline of 3 where the schema carries the heavy lifting for parameter meaning.

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 uses the specific verb 'Create' with a clear resource: 'an empty Markdown or HTML artifact owned by this principal.' It explicitly distinguishes this from the sibling publish_version by stating the artifact is not published initially and directing users to publish_version for the first version. This makes the tool's purpose unambiguous and unique among siblings.

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 direct usage guidance: it explains that creation is the first step and then states 'Use publish_version with expectedLatestVersionId null to publish the first version,' explicitly naming the alternative tool and the condition for using it. This gives clear when-to-use and when-to-use-instead context, fully addressing the most relevant sibling distinction.

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