Skip to main content
Glama

agy_send_input

Send follow-up instructions or review feedback to an existing subagent while preserving conversation context; messages queue if the agent is still running.

Instructions

Send follow-up instructions or review feedback to an existing Antigravity subagent (mirrors native Codex send_input). Preserves full conversation context via --conversation; if the agent is still running, queues the message in its mailbox for the next turn.

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": {
      "agent_id": "<agent_id>",
      "message": "<message>"
    },
    "name": "agy_send_input"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesFollow-up task, correction, or additional constraint.
agent_idYesExisting agent_id from agy_spawn_agent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only give readOnlyHint=false, so the description carries most of the load, and it does: it discloses that conversation context is preserved via --conversation and that delivery is asynchronous — the message is queued in a mailbox for the next turn if the agent is still running. It doesn't cover failure modes (unknown or already-closed agent_id) or whether the call blocks, which are the remaining behavioral gaps.

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 sentences, no filler, with the core action front-loaded and the async-queuing caveat second where it belongs. The 'via --conversation' implementation detail is the only bit that leans toward internals rather than agent-facing meaning.

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 two-parameter mutation with no output schema, the description covers what is sent, what context is retained, and what happens when the target is busy. The one thing an agent might still want — what a successful call returns or how queued delivery is acknowledged — is unstated, but the core call semantics are complete.

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 both parameters are already documented in the schema, and the description adds only the framing that message is a follow-up/correction/constraint and agent_id must be an existing one from agy_spawn_agent. That is a modest semantic layer, consistent with the baseline 3 when the schema does the heavy lifting.

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?

States a specific verb and resource (send follow-up instructions/messages to an existing subagent) and pins the scope with 'existing', which cleanly separates it from agy_spawn_agent. The parenthetical mirroring of native Codex send_input gives an additional anchor for agents already familiar with that API.

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?

The word 'follow-up' plus 'existing Antigravity subagent' tells the agent this is the second-and-later turn after agy_spawn_agent, and the queuing sentence tells it the call is safe to make while the agent is running. It stops short of explicitly naming alternatives or stating when not to use it (e.g., after agy_close_agent), leaving that to inference from sibling names.

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