pdg_dirty

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

With no annotations, the description carries the burden. It discloses important safety and side-effect traits: default does not delete disk output, changes scheduler state, and is irreversible. This exceeds minimal expectations, though it could elaborate on exact scheduler consequences.

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 short and front-loaded with the core purpose. Every word carries weight, but the mixed-language brevity slightly reduces structure clarity.

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?

Despite the tool's complexity (PDG scheduler state mutation), the description omits what 'dirty' does exactly, parameter meanings, and any return/result information. With no annotations or output schema, the description leaves major gaps in operational understanding.

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% for two parameters, and the description provides no explanation of ctx or node_path. The description entirely fails to compensate for the lack of parameter documentation, leaving the agent unable to infer parameter meanings.

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 states a specific action ('dirty work items') and distinct resource, distinguishing it from siblings like pdg_cook and pdg_cancel. It conveys a clear PDG operation, though 'dirty' as a verb may be jargon for non-experts.

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 implies usage (marking work items dirty) and adds cautionary notes (doesn't delete disk output by default, cannot undo). However, it does not explicitly state when to use this tool versus alternatives or provide context-specific guidance.

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