workflow_retention_preview

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

readOnlyHint=true already covers the safety profile, and the description reinforces it consistently with 'without deleting' and 'dry-run'. It goes further by disclosing that the retention daemon runs the identical policy on its next enabled tick, which is useful timing/side-effect context beyond the annotation.

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 core action and its non-destructive nature are front-loaded in the first sentence, and the second sentence adds only relevant context. Slightly awkward paragraphing but no filler lines.

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?

An output schema exists, so return values need not be explained, and the description adequately covers purpose and behavior for a zero-parameter read-only preview. It stops short of pointing to the corresponding apply/commit tool an agent would reach for next.

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 tool takes zero parameters, so the baseline is 4; the schema carries nothing for the description to extend. The description does scope the inspection targets (rows, files, bytes, oldest retained Curator pass), which adds minor meaning without needing parameter detail.

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 (Preview) and resource (terminal Curator/Evolve artifact compaction) with the scope qualifier 'without deleting'. It clearly distinguishes a dry-run read from an actual compaction, but never names a sibling (e.g., db_compact, agent_memory_cleanup, forget) it differs from, leaving cross-tool disambiguation to inference.

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?

'Use this dry-run-first view to inspect candidate rows, files, bytes' gives implied usage context, and the mention of the daemon's next enabled tick hints at the apply step it precedes. However, it names no alternative tool and states no explicit when-not condition, so routing remains inferred.

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