dirty_work_items

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

With no annotations, the description carries the full behavioral burden. It does usefully disclose that remove_outputs deletes output files from disk, but says nothing about whether this marks all items or a subset, whether it requires a subsequent cook, or whether the disk deletion is recoverable.

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 core purpose is front-loaded in one sentence, followed by a compact arg list. The 'ctx: MCP context' entry is boilerplate that adds little, but overall the text is tight and wastes few 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?

For a two-parameter TOP operation with no annotations and no output schema, this is only partly complete: it never states scope (all work items vs. selected), what the agent should do afterwards (cook the node), or what the call returns.

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 adds real meaning for remove_outputs ('Also remove output files from disk'), which is the key non-obvious parameter, but node_path is only restated and no format or expected value is given for it.

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 and resource — marking work items on a TOP node dirty — and clarifies the goal ('so they can be regenerated'). It is clear what the tool does, but it does not distinguish itself from related TOP tools like generate_static_items or cook_top_node, which an agent must choose between.

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 'so they can be regenerated' implies the usage context (forcing re-cook/re-generation), but there is no explicit when-to-use guidance and no mention of alternatives such as cooking, cancelling, or inspecting work item states. Usage is left to inference.

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