Skip to main content
Glama

Ogen

by com.ogenhq
OverviewDiscussionsAdmin

Commit a gated action

commit_gated_action

Ask whether an action of this kind is authorized. Ogen says yes only when it is sure; anything else waits for a person, and it never guesses. Ogen never performs the action itself — your own system does that once this says yes. An unregistered kind is refused. Free tier: only the demo kinds. Record: any registered kind. Once a person confirms, calling again with the same kind returns disposition "released" and a release_ticket — give it to the system that runs the action.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
argsNoOptional: the arguments you will run the action with. Ogen keeps only their fingerprint, for the release ticket a confirmation issues.
kindYesAn action kind, e.g. one registered with register_action.
principalNoTHE HOSTED REQUESTER: required when this kind was registered with approver "principal" — the hold then waits for the person named here, never a registered approver. Refused for any other kind. Nothing but the address.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / principal
      Added value: +{
+  "additionalProperties": false,
+  "description": "THE HOSTED REQUESTER: required when this kind was registered with approver \"principal\" — the hold then waits for the person named here, never a registered approver. Refused for any other kind. Nothing but the address.",
+  "properties": {
+    "email": {
+      "description": "The address of the person the agent is acting for.",
+      "format": "email",
+      "type": "string"
+    }
+  },
+  "required": [
+    "email"
+  ],
+  "type": "object"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / args
      Added value: +{
+  "additionalProperties": {},
+  "description": "Optional: the arguments you will run the action with. Ogen keeps only their fingerprint, for the release ticket a confirmation issues.",
+  "type": "object"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden — and it discloses the fail-safe policy ('says yes only when it is sure... never guesses'), the human-escalation path, the refusal of unregistered kinds, and the tier limits. It stops short of enumerating the other dispositions (only 'released' is named) or stating auth/rate-limit requirements, so it is rich but not exhaustive.

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?

Front-loaded with the core question and the key non-execution caveat. Dense and mostly waste-free, though the tier/permission fragment ('Free tier: only the demo kinds. Record: any registered kind.') is telegraphic and the release-ticket flow could be tightened.

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?

With no output schema, the description supplies the return semantics an agent needs (disposition and release_ticket, plus the re-call protocol), covers the nested principal object's effect, and explains error behavior for unregistered kinds. Nothing essential to calling it correctly is missing.

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 the schema already documents kind, args fingerprinting, and the principal/approver-matching rule in detail. The description adds only the flow context around those parameters rather than new per-parameter meaning; 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 operation ('ask whether an action of this kind is authorized') and immediately distinguishes itself from siblings: 'Ogen never performs the action itself — your own system does that.' An agent can tell this gate apart from register_action, report_outcome, or reverse without opening a 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 the when (before your system runs an action), the when-not (unregistered kinds are refused; free tier limited to demo kinds), and the follow-up path (call again with the same kind after a human confirms). Explicit lifecycle guidance rather than implied usage.

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

All Ogen toolsInspect
Try in Browser
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources