Skip to main content
Glama

Gemini progress digest for a ZCode task

zcode_progress
Read-only

Generate a cached Gemini Flash digest of a subagent task's progress, including summary, done/doing/next, progress percentage, on-track status, concerns, and attention flags; refresh to bypass cache.

Instructions

Cheap Gemini Flash digest (via the agy CLI) of what the task's subagent has done so far: summary, done/doing/next, an estimated progressPct against the task prompt, onTrack, concerns and needsAttention. Works while the task runs and after it finishes (summary of the whole run). Digests are cached per task for ZCODE_MCP_SUMMARY_MIN_SEC seconds (default 300) and only recomputed when new activity exists; set refresh to bypass the cache. For unattended watching prefer bin/zcode-watch.mjs (see README) over polling this.

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_progress"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskIdYes
refreshNoForce a fresh digest, ignoring the cache.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond readOnly/openWorld annotations, it discloses cost character ('cheap'), the cache window via ZCODE_MCP_SUMMARY_MIN_SEC with its 300s default, that digests are only recomputed when new activity exists, and that refresh bypasses the cache. It also clarifies the tool is safe to call both mid-run and post-run, which annotations alone could 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.

Conciseness5/5

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

Three sentences, front-loaded with the core purpose and return fields, then caching behavior, then the alternative. No filler; the parenthetical '(via the agy CLI)' is the only near-optional detail.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so by enumerating every digest field. Combined with the cache lifetime and the polling alternative, an agent has everything needed to call it correctly and interpret the result.

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 coverage is 50%: refresh already has a description in the schema, and the description only reinforces it via the cache context. taskId gains little beyond 'the task's subagent' and 'task prompt' — the session-id pattern comes entirely from the schema, not the prose.

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

Purpose5/5

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

The description names a specific verb and resource ('Gemini Flash digest ... of what the task's subagent has done so far') and enumerates the payload fields (summary, done/doing/next, progressPct, onTrack, concerns, needsAttention), which tells an agent exactly what it gets back and how it differs from a plain status/result call.

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

Usage Guidelines4/5

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

It gives clear usage context — valid while the task runs and after it finishes — and an explicit when-not ('For unattended watching prefer bin/zcode-watch.mjs over polling this'). It does not name MCP sibling alternatives such as zcode_status or zcode_result, so the routing is only partly complete.

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