Skip to main content
Glama
SynapCores MCP Server

SynapCores MCP Server

Official

Inspect an agent's learned state

agent_soul
Read-onlyIdempotent

Inspect an agent's learned memory, episodes, rewards, runs, plans, goals, skills, policy, or audit by database and section to audit behavior and decisions. Admin required; read-only, paginated.

Instructions

Inspect the current tenant/database's learned memory, episodes, rewards, runs, plans, goals, skills, policy or audit, one section per call. Use it to review or audit what an agent has learned and why it acts as it does; use query for ordinary SQL tables. Administrator required; read-only, paginated, no execution.

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": {
      "database": "<database>",
      "section": "<section>"
    },
    "name": "agent_soul"
  }
}

Input Schema

NameRequiredDescriptionDefault
afterNoPagination cursor from the previous page; omit for the first page.
limitNoItems per page, 1 to 100 (default 50).
sectionYesWhich record set to read.
databaseYesDatabase whose agent state to inspect.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.0.1
    • addedInput schema / properties / after / description
      Added value: +"Pagination cursor from the previous page; omit for the first page."
    • addedInput schema / properties / database / description
      Added value: +"Database whose agent state to inspect."
    • addedInput schema / properties / limit / description
      Added value: +"Items per page, 1 to 100 (default 50)."
    • addedInput schema / properties / section / description
      Added value: +"Which record set to read."
  2. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses that administrator privileges are required, that results are paginated, and that nothing is executed. Those are real operational facts the agent could not infer from the annotation block. It stops short of describing what a returned item looks like or how cursors expire, which keeps it from a 5.

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, front-loaded with the purpose and followed by routing and operational constraints; little wasted text. The section list is somewhat run-on and partially redundant with the enum, which costs a point.

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?

There is no output schema, so the description bears more burden to convey what a page of results contains; it says only that reads are paginated and sectioned, without describing item shape or ordering. For an admin-only, read-only inspection tool that is adequate but leaves a real gap, especially given the 12 distinct sections whose contents differ substantially.

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 100%, so the schema already explains `database`, `section` (with its full enum), `limit`, and `after`. The description only loosely mirrors this by naming a subset of sections — notably omitting `plan_steps`, `tenant_fence`, and `tenant_audit`, which appear in the enum — and adds no cursor or paging semantics beyond the word "paginated". Baseline 3 is appropriate since the schema carries the detail.

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 ("inspect") and resource ("learned memory, episodes, rewards, runs, plans, goals, skills, policy or audit") and scopes it to the current tenant/database with "one section per call". It also names the sibling it is not (`query`) and the boundary ("ordinary SQL tables"), so an agent can distinguish the two without opening either 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?

Gives an explicit use case ("review or audit what an agent has learned and why it acts as it does") and an explicit alternative with the condition that selects it ("use `query` for ordinary SQL tables"). The "one section per call" constraint further tells the agent how to structure repeated calls rather than trying to fetch everything at once.

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