Revalidate a learning task after human or model review, then continue only when verification passes; optionally restart an idle dispatcher.
After actual model review/human verification, revalidate the same task before proceeding.
| Name | Required | Description | Default |
|---|---|---|---|
| restart_idle_dispatcher | No |
Changes observed during successful MCP inspections.
v1.9.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden and largely fails: it does not say whether the task is re-executed from scratch or continued, what happens to in-flight state, or whether the operation is idempotent. The single hint is "revalidate the same task before proceeding," which is too vague to infer side effects from.
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?
It is a single short sentence with the precondition front-loaded, so there is no waste. However, the brevity comes from under-specification rather than efficiency — one sentence is not enough to carry the meaning a zero-annotation tool needs.
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?
With no annotations, no output schema, an undocumented parameter, and ambiguous purpose, the definition leaves major gaps: what the tool returns, what state it mutates, and how it differs from the many batch/task-recovery siblings. The precondition sentence alone is insufficient for a stateful batch operation.
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% and the one parameter, restart_idle_dispatcher, is never mentioned. The description does not explain what restarting the idle dispatcher would do or when an agent should set it true, so it adds no meaning over the bare boolean default of false.
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 says "revalidate the same task before proceeding," which does not state that this resumes a paused/stopped learning batch, and never uses the words the tool name implies (resume, batch). Against siblings like start_learning_batch, stop_learning_batch, recover_current_task and route_learning_task, an agent cannot tell what this does or which one to pick.
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 clause "After actual model review/human verification" does give an explicit precondition for calling it, which is more than nothing. But there are no exclusions, no naming of alternatives (start_learning_batch vs recover_current_task), and no explanation of what state the batch must be in for a resume to make sense.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.