aiworkhub_manager_task_decomposition_preview

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

readOnlyHint=true already declares the safety profile, and the description reinforces it with 'never creates or launches tasks' while adding genuinely new information: the result is an advisory digest that is not self-executing. That downstream-decision requirement is exactly the behavioral context annotations cannot express. It does not mention whether previews are persisted or repeatable, so not a 5.

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?

Three short lines, front-loaded with the operation and its read-only nature, then the constraint and the consequence. No filler, and the most consequential fact (never creates tasks) is placed early.

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?

The existence of an output schema means return values need not be explained, and the non-mutation guarantee is covered. But for a 4-required-parameter tool with nested objects and 0% schema descriptions, the description leaves the agent unable to construct valid arguments without opening the schema and guessing at shapes.

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% with 4 required parameters including two nested objects (source_graph_receipt, children), so the description carries full burden and adds almost nothing. 'Source Graph-grounded' hints that source_graph_receipt is evidence linkage, but parent_task_id, objective, and the expected child object shape remain completely undefined in both schema and 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?

States a specific verb and resource: 'validate a Source Graph-grounded child-DAG proposal'. The 'MANAGER READ' prefix and DAG/decomposition vocabulary separate it from the many loop, roadmap, and task-mutation siblings. It stops short of naming a specific alternative tool, so it does not earn a 5.

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?

'MANAGER READ' plus 'requires a separate explicit manager decision' implies this is a pre-decision, non-committal step, which is useful routing context. However, no sibling is named, no prerequisites are stated (e.g. that a source-graph receipt must already exist), and there is no explicit when-not-to-use guidance among the ~180 siblings.

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