OMENZ agent tools

locker_put

Agent Locker: check a job's working state in (resume packet: objective, decisions, open_items, facts, permissions, next_action, pointers; any JSON object up to 64 KB) so it stops filling your context. Encrypted at rest with a key only you get back; kept up to 30 days. Optional 'to' turns it into a handoff to another agent. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/locker/put, $0.002 via x402.)

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": {
      "packet": "<packet>"
    },
    "name": "locker_put"
  }
}

Input Schema

Name	Required	Description
`to`	No	Optional recipient label for handoffs
`from`	No	Optional sender label
`packet`	Yes	Resume packet, any JSON object up to 64 KB
`ttl_days`	No	1-30, default 7

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

B3.3/5.0

Behavior4/5

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

With no annotations, the description carries the whole load and does substantial work: encrypted at rest, a key returned only to the caller, 30-day maximum retention, a 64 KB payload cap, and handoff semantics when 'to' is set. Gaps remain around overwrite/collision behavior and what exactly the response contains, but this is well above the no-annotation baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The key facts (what goes in, encryption, retention, handoff) are front-loaded, but the leading clause is awkward and the trailing 'By OMENZ / AYNE playzone / x402 pricing' parenthetical is promotional and operational noise for an agent deciding how to call the tool.

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?

For a four-parameter write tool with no output schema, the definition covers storage format, size limit, retention bound, encryption, and the handoff mode, which is enough to call it correctly. Only the return value (the key) and overwrite behavior are left semi-implicit.

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 'to', 'from', 'packet' and 'ttl_days' are already documented. The description adds some meaning beyond the schema by enumerating typical packet fields and tying the 30-day ceiling to the ttl range, but it does not explain how 'from' behaves or what 'to' changes server-side.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The core verb is muddled: 'check a job's working state in' reads closer to a read/inspect operation than the write implied by locker_put. The parenthetical eventually clarifies that it stores a resume packet (objective, decisions, open_items, etc.), but an agent skimming the first clause could confuse it with locker_get, which is never named.

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?

Usage is implied rather than stated: 'so it stops filling your context' signals the offload-context use case, and 'optional to turns it into a handoff' clearly delineates the handoff variant. Missing is any explicit when-not guidance or a pointer to locker_get for retrieving the packet back.

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

All OMENZ agent tools tools Inspect

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

Need Help?