Skip to main content
Glama

governance-platform

by ai.geodesiclabs
OverviewDiscussionsAdmin

govern_inference

Quality-govern an in-progress AI generation step BEFORE its output is used (complements validate, which checks finished documents). Returns an action - STOP, CONTINUE, REPAIR_REGION, REUSE_MOTIF, REVIEW, ESCALATE - with a plain-language explanation. Structural scores do not establish task correctness. Check safe_to_finalize and acceptance coverage. Persistence success is reported; read traces in the same Blueprint namespace.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoFree-form caller label recorded for auditmcp
api_keyYesGeodesicAI API key (gai_...)
payloadYesTask-type payload: generative_text {text,...}; retrieval {query,candidates}; generic {features}
blueprintNoOwned Blueprint namespace for the tracedefault
task_typeYesKind of generation step being governed
step_indexNoStep number within this generation (0-based)
constraintsNoOptional governance constraint config object
inference_idYesCaller-chosen ID grouping the steps of one generation

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / blueprint
      Added value: +{
+  "default": "default",
+  "description": "Owned Blueprint namespace for the trace",
+  "title": "Blueprint",
+  "type": "string"
+}
  2. Changed8 schema fields changed
    • addedInput schema / properties / api_key / description
      Added value: +"GeodesicAI API key (gai_...)"
    • addedInput schema / properties / constraints / description
      Added value: +"Optional governance constraint config object"
    • addedInput schema / properties / inference_id / description
      Added value: +"Caller-chosen ID grouping the steps of one generation"
    • addedInput schema / properties / payload / description
      Added value: +"Task-type payload: generative_text {text,...}; retrieval {query,candidates}; generic {features}"
    • addedInput schema / properties / source / description
      Added value: +"Free-form caller label recorded for audit"
    • addedInput schema / properties / step_index / description
      Added value: +"Step number within this generation (0-based)"
    • addedInput schema / properties / task_type / description
      Added value: +"Kind of generation step being governed"
    • addedInput schema / properties / task_type / enum
      Added value: +[
+  "generative_text",
+  "retrieval",
+  "generic"
+]
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations indicate readOnlyHint=false, so this is a mutating operation, yet the description does not contradict that. It adds valuable behavioral context such as the caveat that structural scores do not establish correctness, the need to check safe_to_finalize and acceptance coverage, and notes on persistence and tracing. This goes beyond the annotations, which are sparse.

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?

The description is dense and efficient, with each sentence adding new information. It front-loads the critical purpose and action list, then covers warnings and supplementary details. No redundant phrasing.

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?

Given the tool's complexity (8 parameters, nested objects, no output schema), the description covers the essential usage context, limitations, and operational details (persistence, tracing). It lacks explicit return-value structure, which the user must infer, but the enumerated actions partially fill that gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters are documented in the schema. The description adds extra meaning by noting the payload depends on task_type and that constraints are optional governance controlsholistically. It also clarifies that inference_id groups steps, which the schema mentions but the description reinforces.

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?

The description clearly states the tool's purpose: to quality-govern an in-progress AI generation step before output is used, and distinguishes it from a sibling tool (validate) that checks finished documents. It also lists the specific action results, making the tool's function unambiguous.

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

Usage Guidelines4/5

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

The description explicitly mentions when to use this tool ('BEFORE its output is used') and contrasts it with a sibling tool (validate), providing context for when it applies. However, it does not explicitly state when not to use it or mention alternatives beyond the one sibling.

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

All governance-platform toolsInspect
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