emu_preview_artifacts

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

With no annotations and no output schema, the description carries the full burden but discloses only a negative behavioral trait ("without publishing them"). It never reveals what a preview returns, whether it is idempotent, whether it caches or persists anything, or what permissions are needed, leaving the agent to guess at the operation's observable effects.

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?

Seven words, the action verb leads, and there is zero filler. Every word earns its place.

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 straightforward 1-param tool this is nearly adequate, but the entire purpose is the preview output, and the description says nothing about what the tool returns. Since no output schema exists, this gap is squarely the description's responsibility and remains unaddressed.

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 coverage is 0%, so the description must compensate, yet it never clarifies whether the sole `id` refers to a session, artifact, or batch identifier. The 0% schema coverage plus zero clarification means the description fails to substitute for the missing schema documentation.

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?

"Preview" is a specific verb and "session-derived artifacts" a clear resource. The phrase "without publishing them" meaningfully distinguishes it from the emu_publish_* family, so an agent can tell it apart from siblings without opening the schema.

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 clause "without publishing them" implies this is the safe, non-committal alternative to publication flows, but it never names an alternative (e.g., emu_publish_cdr) nor gives a condition for when to choose this over emu_list_artifact_batches or emu_create_evidence_bundle. The usage is implied by contrast rather than stated.

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