Skip to main content
Glama

router_slots

Query local inference slot occupancy, queue depth, and wait times; preview routing by task and sensitivity; and dispatch adjudication decisions via L0/L1/L2 triage—keeping data local.

Instructions

查询本地推理槽位态(占用 / 排队深度 / 各请求等待时长)+ 路由预览(任务×敏感度 → 去向决策 + routeReason)+ 判定链接入去向下达(adjudicate:IntentTriage L0/L1/L2 判定 → 映射分级 → decideAndDispatch)。运维可见,数据本地不出门。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
refsNo判定链结构化解引用(adjudicate 用——供 L0 先判)
textNo判定链语义输入文本(adjudicate 用)
actionNo动作:snapshot 查槽位态(缺省)/ route-preview 预览路由决策 / adjudicate 判定链接入去向下达snapshot
priorityNo排队优先级(adjudicate 用)
in_domainNo是否在判定域内(adjudicate 用;false → SKIP 走 L0 兜底)
max_slotsNo槽位上限(snapshot 空态时用;缺省 5)
questionsNo判定链问句集(adjudicate 用——缺省单问句 choice[allow,deny])
task_classNo任务类型(route-preview 用)
sensitivityNo数据敏感度(route-preview / adjudicate 用)
critical_nodeNo⚡ 节点(adjudicate 用——强制 ASK)
cloud_availableNo云端可用性(route-preview / adjudicate 用)
local_availableNo本地可用性(route-preview / adjudicate 用)
evidence_readinessNo证据就绪度(adjudicate 用——缺省 none)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.4

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It adds real context: ops-only visibility ('运维可见') and a data-locality guarantee ('数据本地不出门'), and discloses that adjudicate actually dispatches a routing decision. However, it never states what side effects dispatch has, what permissions are needed, or reversibility of an adjudication, so the safety profile remains under-specified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single dense sentence with no wasted filler and the default snapshot mode is front-loaded. But the heavy jargon and three concatenated verb clauses make it hard to parse quickly, which offsets the compactness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, annotation-free, multi-mode tool the description does cover the three actions and hints at return content (queue depth, wait time, routeReason). It relies on the schema for the rest and there is no output schema, leaving the exact response shape and the decision pipeline incomplete for such a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema (including which mode each serves). The description restates the parameters associated with each action but adds no format, default, or interaction detail beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names three concrete verbs/resources driven by the action enum: snapshot (slot occupancy/queue depth/wait time), route-preview (task × sensitivity → destination + routeReason), and adjudicate (IntentTriage L0/L1/L2 → mapping → decideAndDispatch). An agent can tell what each mode does. It does not differentiate itself from the sibling router_session_push, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mirrors the schema's action semantics (snapshot default, route-preview for preview, adjudicate for dispatch), so usage is implied rather than explicitly stated. There is no when-not-to-use guidance and no routing to alternatives such as router_session_push or route_workflow. Adequate but leaves the selection reasoning to inference.

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

Deploy Server

Other Tools