Skip to main content
Glama

Start a structured ZCode task

zcode_run_structured
Destructive

Initiate a ZCode session with a bounded JSON schema and optional domain rule preset to enforce structured output, then fetch results via zcode_structured_result.

Instructions

Start a normal ZCode session with a bounded JSON schema contract and optional domain semantic rule preset (e.g. section-outline-v1, or a declarative rule object). This uses subscription quota and FULL ACCESS like zcode_run. The schema and domainRule are stored in the session prompt; use zcode_structured_result after completion.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>",
      "input": "<input>",
      "schema": "<schema>"
    },
    "name": "zcode_run_structured"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYes
inputYes
modelNo
schemaYes
providerNo
domainRuleNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds meaningful context beyond them: it consumes subscription quota, runs with FULL ACCESS, and the schema/domainRule are persisted into the session prompt. What it does not explain is what 'destructive'/FULL ACCESS concretely risks or how a session is torn down, so it is strong but not exhaustive.

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 focused sentences, front-loaded with what the tool does, followed by cost/access caveats and then the follow-up tool. Every sentence contributes; density is high but readable, with no filler.

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 mutation tool with no output schema and 0% schema coverage, the description covers workflow (result retrieval via zcode_structured_result) and cost/permission posture well. It omits what starting actually returns — e.g. a session/job identifier that zcode_structured_result would need — which is the main gap an agent must have filled to chain the calls.

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 0% across 6 parameters, so the description must carry the load; it does explain 'schema' (bounded JSON schema contract) and 'domainRule' (preset enum or declarative rule object), which are the two most ambiguous nested params. It says nothing about task vs input, model, or provider, leaving half the parameters undifferentiated.

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?

Specific verb+resource: 'Start a normal ZCode session with a bounded JSON schema contract'. It distinguishes itself from zcode_run by the schema/domainRule contract and points at zcode_structured_result for retrieval, so an agent can tell it apart from the plain run tool. It stops short of explicitly framing itself as the structured alternative to zcode_run, leaving a small inference.

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?

It gives clear post-call routing ('use zcode_structured_result after completion') and cost context (subscription quota, FULL ACCESS), which implies when to pick it: whenever the caller needs a JSON schema contract. However, it never explicitly states when to prefer this over zcode_run or swarm_run_structured, so the selection guidance remains 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.