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

Annotations already flag non-read-only, open-world, and destructive semantics. The description usefully narrows the side-effect surface to metadata only (never code/content) and names capability requirements, though it does not detail the destructive implications flagged by destructiveHint.

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 definition, one-line scope limitation, and compact routing guidance. The field details are brief and the capability notes are grouped without repetition.

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?

Includes return shape, capability requirements, sibling distinctions, and the at-least-one-parameter rule. It doesn't enumerate error cases, but for a simple metadata update with full schema coverage and a return description this is reasonably complete.

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 description adds meaning beyond the schema: at least one of name/privacy must be sent, both may be set in one call, and sessionId can be derived from the artifact URL. This directly resolves ambiguity not present in the schema.

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?

Opens with a precise definition: update metadata (name/visibility) on an existing artifact, and explicitly says it is not for code/content. This cleanly separates it from artifact-edit and artifact-publish.

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 routing guidance: use artifact-edit for code/content changes, artifact-publish for publishing, and artifact-create for new artifacts. It also says sessionId comes from an existing artifact and how to extract it from a URL.

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