preview_deletion

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), but the description adds real behavioral detail beyond them: mixed research artifacts are marked stale, while originals, old exports, backups, and provider data are retained. This consequence-disclosure is genuinely useful and not derivable from structured fields.

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?

Purpose is front-loaded in the first clause, followed by consequence and retention details. It is a single dense sentence with no filler, though the trailing retention list is somewhat list-like rather than prose.

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?

With no output schema and read-only annotations, the definition provides enough context to call it (what is affected, what is preserved). The main gap is the unexplained work_id format, but the impact-preview contract itself is well communicated.

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 0% for the single required work_id parameter, so the description must compensate and it does not: it references '文献' (work) only loosely and gives no format, identifier type, or example for work_id. The one parameter remains semantically opaque.

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 states a specific verb (预览/preview) and resource (删除文献及关联索引/deleting a work and its associated indexes), which is precisely separable from the sibling delete_work that performs the actual deletion. An agent can tell it is an impact-assessment preview rather than the destructive operation itself 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 framing strongly implies this should be run before delete_work, but the description never explicitly states when to use it, when not to, or names the delete_work alternative. Usage is left to inference rather than spelled out.

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