cleanup_all

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

With no annotations provided, the description carries full responsibility and does exceptionally well. It explicitly lists what gets cleared (three directories), what is preserved by default (config/ and models/), what happens when flags are true, that the database is untouched, and that the tool returns per-directory statistics and retained items. This fully discloses the destructive impact.

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 description is concise and well-structured: an opening declarative sentence followed by two bullet points for the parameters, plus a final note on database behavior and return value. Every sentence contributes necessary information with no fluff.

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 annotations and two parameters, the description is complete. It covers side effects, default safe behavior, optional destructive extensions, exclusion of the database, and the return format. The 'factory reset' analogy provides helpful mental context, and the output schema is provided separately.

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%, so the description must compensate. It does so thoroughly: include_config and include_models are each explained with their defaults, effects, and rationale (e.g., models are expensive to re-download). This adds meaning far beyond the bare boolean schema.

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 clearly states the tool's purpose: '全局清理（类似恢复出厂）' (global cleanup, similar to factory reset) and lists the exact resources it affects (note_results / static/screenshots / logs). This distinguishes it from the sibling tool cleanup_note, which is per-note, by emphasizing global scope.

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 description provides clear context for when to use this tool: it's a global cleanup affecting all task artifacts. It explains default behavior (preserving config and models) and conditions for extending cleanup via include_config and include_models. However, it does not explicitly mention alternatives like cleanup_note or state 'do not use for per-note cleanup,' so it falls short of a perfect 5.

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