delete_work

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

Annotations already flag destructiveHint=true/readOnlyHint=false, but the description adds non-obvious behavior: the call is gated on human confirmation and the digest acts as a staleness guard so the blast radius cannot drift from the preview. It still doesn't say what is destroyed, whether it is recoverable, or what a digest mismatch returns.

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?

A single sentence with the gating condition front-loaded and no filler. It is tight, though the single clause bundles two distinct requirements (explicit user request and preview review) that could be easier to parse if split.

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 destructive, 2-required-param tool with no output schema, the description covers the critical safety workflow (preview plus digest) but omits the consequences of success (what exactly is removed, whether backup_library should be used first) and the failure mode when the digest is stale.

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 carry parameter meaning; it usefully explains that 'inventory_digest' comes from the preview and exists to detect scope changes, which the schema alone does not convey. work_id is left entirely to the name, so only half the parameters are meaningfully covered.

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 verb '删除' (delete) appears only inside a precondition clause, so the tool's actual operation is inferred from the name rather than stated (e.g., it never says a work record and its dependent artifacts are removed). Siblings like preview_deletion, backup_library and restore_library are not named or contrasted, so differentiation is left to the agent.

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 an explicit, testable precondition: call only after the user explicitly asks for deletion AND has seen the latest preview. That is real when-to-use guidance rather than an implied context. It stops short of naming preview_deletion as the required preceding tool or stating what to do when no preview exists.

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