memory_organize

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

With no annotations, the description carries the full burden. It discloses that the tool is 'safe' by default but notes that the 'full' target can be destructive (purge) and requires confirmation. It also explains the dry_run option for previewing changes. This provides good insight into the tool's behavior, though it could further detail what each operation does (e.g., compact, dedup).

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. It starts with the main purpose, then lists targets and arguments in a clear bullet-point format. Every sentence provides necessary information without redundancy.

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?

Given the complexity of the tool (multiple targets, destructive potential) and the lack of schema descriptions, the description is complete. It covers what the tool does, the available targets, argument details, and safety considerations. The presence of an output schema means return values need not be described.

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 input schema has 0% description coverage, so the description must compensate. It does so excellently: it explains the possible values for 'target' (safe_default, full, compact, dedup) and conditions for 'confirm' (required when target='full' and dry_run=False). This adds meaning far beyond the schema's bare type definitions.

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: 'Run safe memory maintenance batch.' It specifies the verb 'run' and the resource 'memory maintenance batch'. The listing of different targets (safe_default, full, compact, dedup) further clarifies the scope. This distinguishes it from sibling tools, which have names like memory_save, memory_search, etc., indicating different functions.

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?

While the description does not explicitly compare this tool to alternatives, it provides clear context on when to use it by detailing the available targets and their compositions. It implies that this tool is for automated batch maintenance, which is distinct from individual operations like save or delete. However, no explicit guidance on when not to use it or contrasts with siblings is given, preventing a perfect score.

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