laya-mcp

Answer a typed question set about some context

decide

Read-onlyIdempotent

Answer typed questions about state in one pass, returning calibrated answers and a contract grade so agents act only when auto_execute.

Instructions

Answer a typed question set about state in one forward pass.

Returns calibrated answers plus a contract directive. Branch on contract.grade: act only when it is auto_execute. Compose a preset with inline questions to answer both in the same pass.

Input Schema

TableJSON Schema

Name	Required	Description
`lang`	No	Hint the state's language to skip detection (e.g. 'zh', 'en')
`task`	No	Force the typed-decisions checkpoint for its four workflows
`model`	No	Force a checkpoint: english \| multilingual \| typed-decisions
`state`	Yes	Context to decide about: a string, or an object/list for structured input (code, ticket, diff, agent trace, tool result). Include the raw material, not a summary of it.
`preset`	No	Named question set: code_change_risk, support_triage, input_guard, routing, typed_decisions_agent_trace
`questions`	No	Questions to answer, keyed by question id. Each: {kind: choice\|score\|yes_no, instructions, criteria, weight?}. Choice criteria: {label: when-to-pick}. Score criteria: ordered level list. yes_no criteria: {true: statement-that-should-hold}.
`threshold`	No	Confidence required to grade an answer auto_execute: a number in [0,1] or a named level (trivial=0.60, low=0.70, normal=0.80, high=0.90, critical=0.95). Defaults to the server's normal level.
`use_cache`	No	Reuse an identical in-process answer

Output Schema

TableJSON Schema

Name	Required	Description
`grade`	Yes	Overall grade; act autonomously only when this is auto_execute
`usage`	No
`cached`	No	True when served from the in-process cache
`answers`	Yes
`routing`	Yes
`summary`	Yes
`contract`	Yes	Directive: overall grade, per-question grades, and the reasons for them
`autonomous`	Yes	True when every answer cleared the auto-execute bar
`latency_ms`	Yes	Server-side inference time
`requires_human`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Sep 29, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld=false, so the bar is low, and the description adds real context: answers are 'calibrated', a `contract` directive is returned, and the grade gates action. It also notes a one-forward-pass execution model, which the annotations do not convey.

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

Conciseness4/5

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

Three short sentences, front-loaded with the core action, and each sentence carries information (what it does, what it returns, how to compose). No filler or restatement of the name.

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

Completeness4/5

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

With an output schema present, return values need not be spelled out, yet the description still explains the `contract.grade` field's significance. Combined with 100% schema coverage on 8 parameters, the definition is nearly complete for correct invocation; only sibling routing is missing.

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 parameters are fully documented structurally, establishing a baseline of 3. The description adds one genuine semantic point – that a `preset` can be composed with inline `questions` in the same pass – but otherwise repeats the schema's job.

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 states a clear verb+resource ('Answer a typed question set about `state`') and clarifies the scope ('in one forward pass'). It is distinguishable from siblings like decide_yes_no and decide_shortlist by the word 'typed', but it never explicitly contrasts itself with them, so the differentiation is inferential rather than stated.

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 only usage direction is about consuming the result: 'act only when it is `auto_execute`'. That is useful downstream guidance, but there is no when-to-use-this-vs-a-sibling guidance despite three closely related decide_* tools existing. Usage is implied rather than stated.

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

Deploy Server