Skip to main content
Glama
Sign In

SKV Network

by network.skv
OverviewDiscussionsAdmin

memory_recall_later

Deep background memory search (query + search_as statement forms, both in the memory base_language) when turn/memory_search found nothing reliable: on-server agent collects ranked evidence (~10-30 s, ~0.1 RUB). Returns job_id; poll memory_recall_status(job_id).

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": {
      "query": "<query>"
    },
    "name": "memory_recall_later"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe question in the memory base_language (turn/step_zero report base_language); keep names and exact terms.
search_asNoOptional, recommended: the same up to 3 statement forms you passed to turn/memory_search (how the answer was most likely WRITTEN in memory, base_language, keep names, never invent the unknown fact). Used as an extra seed of the deep search.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / query / description
      Added value: +"The question in the memory base_language (turn/step_zero report base_language); keep names and exact terms."
    • addedInput schema / properties / search_as
      Added value: +{
+  "anyOf": [
+    {
+      "items": {},
+      "type": "array"
+    },
+    {
+      "type": "string"
+    }
+  ],
+  "description": "Optional, recommended: the same up to 3 statement forms you passed to turn/memory_search (how the answer was most likely WRITTEN in memory, base_language, keep names, never invent the unknown fact). Used as an extra seed of the deep search."
+}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, and the description carries the full burden well: it discloses that the work happens on-server, that it is asynchronous (returns job_id, must poll), and quantifies latency (~10-30 s) and cost (~0.1 RUB). Those are exactly the traits an agent needs to decide whether to invoke a long-running, paid operation.

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?

Dense but front-loaded: purpose first, then the alternative condition, then cost/latency, then the async contract. The slash-compressed phrasing ('turn/memory_search', 'base_language', '~0.1 RUB') assumes project vocabulary and is slightly hard to parse on first read, but nothing is wasted.

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 2-parameter async job tool with no output schema, everything needed to call it correctly is present: when to use it, what the inputs mean, that it is non-blocking, and which tool to poll. Return-value detail is legitimately delegated to memory_recall_status.

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 parameters are already documented; the description still adds workflow meaning by tying both parameters to the base_language requirement and framing search_as as 'an extra seed of the deep search'. It does not add formatting or encoding detail beyond the schema, so it stays a step above baseline rather than a full 5.

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+resource ('Deep background memory search') and immediately scopes it against the sibling it complements ('turn/memory_search found nothing reliable'). An agent can distinguish it from memory_search, memory_recall_status, and memory_start without opening any schema.

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?

Explicit trigger condition: only use after turn/memory_search returned nothing reliable. It also names the required follow-up tool (memory_recall_status with job_id), so the full use/poll loop is spelled out with no inference required.

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

All SKV Network toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources