dl_cleanup_apply

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so safety is partly covered. The description adds a genuinely useful behavioral guard beyond them: it deletes only the exact objects that match an unchanged preview, implying drift between preview and apply causes deletion to be skipped or rejected.

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 tightly-written sentence with the safety constraint front-loaded. No filler or 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?

For a destructive tool with no output schema, zero schema description coverage, and nested object parameters, the description covers intent and the preview-freshness safety contract but says nothing about the structure or content expected inside the two nested parameters.

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% and both parameters are nested objects with no inner descriptions, so the description must carry the load. It does clarify the semantics of 'preview' (must be unchanged) and 'confirmed_delete' (the exact ordered objects), but gives no hint about the nested shape or fields either parameter requires.

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 (delete) and a specific scoped resource (the exact ordered objects confirmed from an unchanged cleanup preview), and implicitly distinguishes itself from the dl_cleanup_preview sibling. It stops short of naming what kind of objects are deleted, so the resource remains somewhat abstract.

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 phrase 'confirmed from an unchanged cleanup preview' encodes a clear prerequisite workflow: a preview must exist and must not have changed before this call is safe. It does not explicitly name dl_cleanup_preview as the required precursor, leaving the agent to infer the ordering.

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