curator_review

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

With no annotations, the description fully discloses behavior: force bypasses the daemon disabled state, dry_run short-circuits before spawning and returns an inventory with counts. It also clarifies that dry_run does not advance the cursor. This is thorough behavioral transparency.

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 extremely concise—only three short sections—yet every sentence adds value. It front-loads the core action and uses clear bullet-like formatting for parameters. No wasted words.

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 tool's simplicity (2 boolean parameters) and the presence of an output schema, the description covers all necessary context: parameter behaviors, use cases, and return value hints. It is complete for its complexity level.

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?

Despite 0% schema description coverage, the description adds rich meaning to both parameters: force's effect on CURATOR_INTERVAL_S and dry_run's short-circuit and return value composition. This fully compensates for the schema's lack of description.

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 core action: 'Fire one curator pass.' It then elaborates on the two boolean parameters, making the purpose unmistakable. The resource 'curator pass' is specific and distinct from sibling tools like curator_run.

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 explicit usage guidance for both parameters: force=True is for 'one-shot triage or testing the prompt' and works even when CURATOR_INTERVAL_S=0; dry_run=True is to 'inspect what the curator child would see before paying for the spawn.' This clearly informs when to use each mode.

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