Skip to main content
Glama
CROW: LLM Wiki

CROW: LLM Wiki

Official

reply

Submits your answers to a job's pending memory requests and returns the next requests or final result. Use it only after recall, remember, remember_file, sync_folder or rebuild returns a job.

Instructions

Send your answers to the memory's pending requests; returns its next requests or the final result.

Call it only after recall, remember, remember_file, sync_folder or rebuild returned a job: the memory then works with your models. Answer each request as its how says, then pass the job and {request id: your reply}. With status "waiting", call it with the job and {} until the work ends. Each call waits up to 50 seconds and returns new requests, or {status: "done", ...} with the result the first tool would have given. A job's result is kept 10 minutes after it ends.

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": {
      "job": "<job>",
      "replies": "<replies>"
    },
    "name": "reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYesThe `job` id that recall, remember, remember_file, sync_folder or rebuild returned
repliesYesYour reply to each request, by its id: {"r1": "…"}; {} while waiting

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.5
    • changedInput schema / properties / job / description
      Previous value: -"The job that recall or remember returned"New value: +"The `job` id that recall, remember, remember_file, sync_folder or rebuild returned"
    • changedInput schema / properties / replies / description
      Previous value: -"Your reply to each request, by its id: {\"r1\": \"…\"}"New value: +"Your reply to each request, by its id: {\"r1\": \"…\"}; {} while waiting"
  2. First observedv1.0.4

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare it is a non-destructive, non-open-world non-read; the description adds the behavior that actually matters: each call blocks up to 50 seconds, calls must be repeated while waiting, and a job's result is retained only 10 minutes after it ends. Those are non-obvious operational facts (latency, polling loop, expiry) that no structured field conveys.

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?

Four tight sentences, front-loaded with purpose, then precondition, then loop mechanics, then retention caveat. Density is high but each sentence carries a distinct operational rule; a minor cost is that the job-creation tool list and the waiting loop are stated in near-schematic prose that takes a second read.

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?

For a stateful, long-polling handshake tool with a nested replies object, the description supplies the precondition, the reply format, the loop/termination condition, the timeout, and result expiry. With an output schema present and annotations covering the safety profile, nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by specifying the replies object is keyed by request id and must follow each request's `how`, and that an empty {} is the correct value during waiting states. That is slightly more than the schema prose provides.

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 — sending answers to a memory's pending requests and receiving the next requests or the final result. It also positions itself against the siblings that create jobs (recall, remember, remember_file, sync_folder, rebuild), so an agent can tell it is the continuation step rather than a new query.

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

Usage Guidelines5/5

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

Gives an explicit precondition ('only after ... returned a job') and an explicit loop protocol: answer each request as its `how` says, then call with the job and {request id: reply}; while status is "waiting", call with {} until the work ends. It names both when to use and how to terminate — nothing is left to inference.

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