Skip to main content
Glama

Read an optional ZCode model IO record

zcode_session_model_io
Read-only

Reads a retained model input/output JSONL record for a session, returning metadata and tool names by default and assistant text plus tool arguments when includeContent is enabled.

Instructions

Read one retained model IO JSONL record for a session. Recording may be absent or incomplete. Returns metadata and tool names by default; includeContent also returns assistant text and tool arguments. Never returns request headers or full prompt; not a per-token event stream. Records over 1 MiB are reported and not skipped.

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": {
      "taskId": "<taskId>"
    },
    "name": "zcode_session_model_io"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNo
taskIdYes
includeContentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description adds real behavioral context: recordings may be absent or incomplete, default output excludes content, headers and full prompt are never returned, and records over 1 MiB are reported rather than skipped. The remaining gap is that pagination or cursor behavior is unaddressed.

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

Conciseness5/5

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

Four short sentences, no redundant restatement of the name, and the core scope is front-loaded before the exclusion and size caveats. Every clause carries information the structured fields do not.

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?

For a tool with no output schema, the description adequately covers what comes back (metadata, tool names, optionally assistant text and tool arguments) and its limits. The unexplained 'cursor' parameter and lack of guidance on how multi-record sessions are traversed is the main shortfall.

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?

With 0% schema description coverage, the description does the work for 'includeContent' by spelling out exactly what extra data it unlocks versus the metadata-and-tool-names default, and 'taskId' is implied by the session framing. The 'cursor' parameter is never mentioned in the description or schema, leaving one of three parameters fully opaque.

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 specific verb and resource ('Read one retained model IO JSONL record for a session') and explicitly negates a sibling behavior with 'not a per-token event stream,' which separates its granularity from the events tool. It stops short of naming which sibling to use instead, so it is clear but not fully differentiated by name.

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?

Usage is only implied: 'Recording may be absent or incomplete' tells the agent to expect misses, and 'includeContent also returns...' signals the choice between a light and full read. There is no explicit when-to-use versus alternatives and no stated precondition beyond having a session id.

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