Skip to main content
Glama

record

Save the query, cited node IDs, and optional tool-call steps that produced a grounded answer so agents can reuse prior search paths without caching answer text.

Instructions

Save the path that answered query: the node ids the answer cites, and optionally the tool calls made (each {"tool": name, "args": {...}, "returned": [node ids]}). Never include the answer text.

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>",
      "cited": "<cited>"
    },
    "name": "record"
  }
}

Input Schema

NameRequiredDescriptionDefault
citedYes
queryYes
stepsNo
outcomeNoaccepted

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already flag this as a non-destructive write (readOnlyHint=false, destructiveHint=false, non-idempotent). The description adds real value with the hard constraint 'Never include the answer text' and the exact shape of each step object, but says nothing about what happens on repeated records for the same query, whether prior records are replaced, or what comes back.

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 tight sentences, front-loaded with the core action, then the negative constraint. The inline step-object example earns its space by disambiguating a loosely typed array-of-objects parameter; slightly dense for a first read but no filler.

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?

No output schema exists, so the description should say more about what recording returns and how duplicates are handled, and the unexplained `outcome` enum is a gap for a mutation tool with four parameters. Given the low complexity, the description is close to adequate but missing those pieces.

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 0%, so the description must carry the load; it partially does. It clarifies `cited` (node ids the answer cites) and gives an explicit structure for `steps`, but leaves `outcome` (the enum verified/feedback/accepted) and `query` itself entirely unexplained, so one of four parameters and the enum semantics remain undocumented.

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 concrete action and target: persist the provenance 'path that answered `query`' — the cited node ids plus optional tool calls. An agent understands this is a write-side recording tool, though terms like 'path' and 'node ids' are domain jargon and no sibling (recall/reject) is named to sharpen the boundary.

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

Usage Guidelines2/5

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

Offers only an implicit trigger ('the path that answered `query`'). There is no statement of when to call this versus recall or reject, no prerequisites, and no exclusions — an agent must infer the workflow position entirely from convention.

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

Deploy Server

Other Tools