Skip to main content
Glama

get_agent_versions

Read-only

Retrieve the version history of Otto or Now Assist AI agents and agentic workflows, newest first, including version number, name, state, instructions, and condition. Filter by state or target ID.

Instructions

Get the version history of an Otto / Now Assist AI agent or agentic workflow (sn_aia_version): version number, name, state (Draft/Published), instructions and condition. Newest first.

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": {
      "target_id": "<target_id>"
    },
    "name": "get_agent_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax records (default 25)
stateNoFilter by state, e.g. published, draft
target_idYessys_id of the sn_aia_agent or sn_aia_usecase
target_tableNoOptional target table filter
include_instructionsNoInclude the full instructions text (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.0.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety need not be restated. The description adds value beyond that by disclosing result ordering ('Newest first') and the shape of returned rows, which helps the agent interpret output without an output schema. It does not say how limit/paging behaves when there are many versions, which keeps it below 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that names the resource, the table, the returned fields, and the ordering, with no filler. Every clause carries information an agent would otherwise have to guess.

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?

With 100% schema coverage and no output schema, the description covers the essentials: what is returned, how rows are ordered, and which table backs it. It stops short of describing behavior for unknown target_id values or how limit interacts with result sets, which would be useful for a history-listing tool.

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 all five parameters (limit, state, target_id, target_table, include_instructions) are already documented in the schema. The description's mention of state Draft/Published and of instructions/condition slightly reinforces those params but adds no syntax, format, or edge-case guidance beyond the schema. Baseline 3 applies.

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 ('Get the version history of an Otto / Now Assist AI agent or agentic workflow'), names the backing table (sn_aia_version), and enumerates the returned fields (version number, name, state, instructions, condition). 'Version history' clearly separates it from single-agent readers like get_ai_agent.

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

Usage Guidelines3/5

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

Use is only implied by the description itself — an agent can infer it is for inspecting past versions of an agent, and the schema's state/limit params hint at filtering. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., get_ai_agent for the current definition).

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