Skip to main content
Glama

gemini_task

Runs a named .zwilling/tasks template with optional instructions, files, and git diff for read-only Gemini analysis or second opinions without tool access.

Instructions

Run a named task template from .zwilling/tasks/.md in the project (e.g. explain, test-ideas, migration-plan), with optional extra instructions, files and diff. Gemini still has no tool access. No task templates found in this project yet.

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>"
    },
    "name": "gemini_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
diffNoAttach a git diff: "staged" (index vs HEAD), "working" (unstaged), "HEAD" (all uncommitted changes), a ref, or a range like "main...HEAD". Counts against the size limit.
taskYesTemplate name, read from .zwilling/tasks/<task>.md (letters, digits, - and _).
filesNoPaths relative to the project root (max 20 files, 500 KB total). Also accepts line ranges (src/a.ts:40-120), directories (src/) and globs (src/**/*.ts); globs and directories respect .gitignore. Contents are inlined into the prompt.
modelNoModel ID as listed by `agy models`; the suffix is the reasoning effort, e.g. gemini-3.8-flash-low | -medium | -high. Omit to use the configured default (.zwilling.json, else agy's). Higher effort is slower.
timeout_sNoTimeout for this call in seconds (default 120).
instructionsNoExtra instructions appended to the template.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With only openWorldHint=true annotated, the description does the heavy lifting and does add value: it discloses that Gemini has no tool access (so files/diff must be inlined) and surfaces the runtime state that no task templates exist in this project, warning of likely failure. It never states the operation is a non-mutating LLM call or what the response looks like, so the transparency is partial.

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?

Two compact sentences, front-loaded with the action and template location, and no wasted wording. The trailing 'No task templates found' line is a dynamic state note rather than a durable definition, but it is short and actionable.

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 six-parameter LLM-invocation tool with no output schema, the description omits what the call returns and whether results are logged (read_gemini_log exists). The mention that Gemini lacks tool access and that templates are absent covers the most important runtime caveats, but the response contract remains unaddressed.

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 the six parameters are already fully documented, and the description merely echoes instructions, files and diff without adding format or interaction detail. Baseline 3 is appropriate since the schema, not the description, carries parameter meaning.

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?

States a specific verb and resource: run a named task template read from .zwilling/tasks/<task>.md, with concrete examples (explain, test-ideas, migration-plan) that make the template concept tangible. It does not name or contrast with the obvious sibling ask_gemini, so the agent must infer the freeform-vs-template distinction.

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 through the template examples and the note that Gemini has no tool access, which hints this is a prompt-composition wrapper. There is no explicit 'use this when you have a predefined workflow, use ask_gemini for ad-hoc prompts' routing, and no prerequisites such as needing a template to exist.

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