MCP Path

Semantic Batch Summary

Semantic Batch Summary is a public reference for knowledge signals, learning candidates, and explainable orientation. It names the signal, policy, or flow an agent should understand before choosing a concrete tool.

Catalog path

Reference page for a documented MCP capability path.

Type: MCP path
Family: Learning & Knowledge Evolution
Effect: bounded run
Status: Reference
Path: 11.13

Purpose

What this entry explains

What it does

This reference explains Semantic Batch Summary for knowledge signals, learning candidates, and explainable orientation. It is kept as a named reference so agents can cite the flow without inventing a tool name.

Use when

Use this entry when an agent needs to start or monitor the bounded flow "Semantic Batch Summary" for knowledge signals, learning candidates, and explainable orientation.
Use it as a reference path when the catalog describes a capability but no single public tool name is explicit.
Use it before chaining follow-up tools so the next step is based on current evidence.

Reference Use

How agents should cite and apply this area

Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.

Signal, gate, behavior, boundary

Semantic Batch Summary describes a behavior for knowledge signals, learning candidates, and explainable orientation. The path shows which signal, gate, behavior, or boundary must be checked before choosing a concrete tool.

When agents cite it

An agent cites this path when it needs Semantic Batch Summary as context for a decision, block, target check, or follow-up tool choice.

Why no callable name

The public source does not name one callable tool for this path. The documentation therefore keeps it as a reference path and does not invent a callable name.

Signals and rule

Relevant response signals: pksSemanticLearningBatchSummary. Safety axes: Automation. The reference path alone is not permission to execute. Before acting, check current MCP discovery, visible target, scope, and the actual response.

Family example

A task touches data, identity, or permissions in knowledge signals, learning candidates, and explainable orientation that may be used only with clear purpose.

The agent starts with nova.learn_suggest, reads the current response or reference, and only then chooses the concrete next tool.

nova.learn_suggest nova.learn_generate nova.learn_promote

Sensitive values stay in current scope; they are not guessed, logged, or copied into other contexts.

Contract

Inputs and important response fields

This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.

Inputs

No stable public input field is derived from the catalog source for this path. Read current MCP discovery before execution.

Response field	Explanation
`pksSemanticLearningBatchSummary`	Content-bearing response field. Treat it as current evidence and consider sensitive data before forwarding it.

Safety

Boundary before execution

Effect

Starts or observes a bounded run. Scope, limits, progress, and terminal status need to stay visible.

Agent rule

Treat stored knowledge as guidance only. Before any action, confirm the current page, target, scope, and visible evidence again.

Human control

For humans, this entry shows which bounded flow in knowledge signals, learning candidates, and explainable orientation starts or continues, and where scope, progress, and stopping conditions belong.

High-Impact Review

Execution boundary and recheck hints

Review category: Scheduler/tasks/automation

Execution boundary

Runs need scope, budget, progress, stop condition, and reviewable terminal status before they start or continue.

Typical false assumption

False assumption: once started, a run may continue until success.

Visible user control

Task, schedule, variables, workspace, and run status must remain reviewable by the user.

Agent rule

Bound automations, poll progress, check terminal status, and avoid chaining when results are unclear.

Abort or recheck

Abort or recheck when budget, target set, run ID, workspace, or result status becomes unclear.

Safety Axes

How this path can affect work

Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.

Automation automation_run

Starts or monitors crawls, sequences, schedulers, tasks, batches, or longer runs.

Keep scope, budget, progress, stop condition, and terminal status visible before and during the run.