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

Beyond the annotations, it discloses atomicity, that every version is stored in full and consumes the owner's storage quota, that a stale expectedVersionId produces CONFLICT, and that empty text is valid. These are real behavioral consequences an agent cannot infer from readOnly=false / destructive=false alone.

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?

Front-loaded with the core action, then constraints, then alternatives — no wasted sentences. The storage/quota and prune tail is slightly beyond what is needed to invoke the tool, but it earns its place by steering behavior away from version spam.

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 9-parameter mutation with an output schema and annotations already present, the description covers the operation model, conflict handling, storage cost, and sibling alternatives. Nothing an agent needs in order to call it correctly is missing.

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?

Adds meaning beyond the 78%-covered schema by tying expectedVersionId to the workspace requirement and pointing at currentVersionId as its source, and by framing content vs base64Content as mutually exclusive alternatives. The remaining parameters (why, description, creatorContext, filename, mimeType) get no treatment in the description, but the schema already documents most of them.

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?

States a specific verb and mechanism: atomically create a new version from either text (content) or a base64 file. It also distinguishes itself from siblings by naming artifact_patch for audience changes and artifact_versions_prune for cleanup, so an agent can route correctly without opening other schemas.

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?

Gives explicit when-to-use and when-not-to-use guidance: use artifact_patch to change a workspace audience, use table_append_rows-style tables for record-growing data, and call prune only on the person's request. It also prescribes the conflict recovery loop — re-read, then retry with currentVersionId.

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