Skip to main content
Glama

Kevros — Agentic Identity Trust

by io.github.ndl-systems

Verify Outcome

verify-outcome
Idempotent

Verify that an executed action achieved its declared intent. Closes the loop: intent -> command -> action -> outcome -> verification. Free (included with bind).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_idYesUnique identifier of the agent whose outcome is being verified
intent_idYesID of the original intent from governance_bind
toleranceNoNumeric tolerance for goal matching (0.1 = 10% deviation allowed)
binding_idYesID of the intent-command binding from governance_bind
actual_stateYesObserved end state after action execution, compared against goal_state

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4/5.0
Behavior3/5

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

Annotations already provide idempotentHint=true and destructiveHint=false. The description adds the conceptual loop and mentions 'Free (included with bind)' but doesn't elaborate on side effects or comparison semantics. No contradiction with annotations.

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 two sentences: the first clearly states the purpose, the second explains the workflow and cost. Minimal fluff, efficiently front-loaded.

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?

The description outlines the tool's role in a workflow and mentions 'Free (included with bind)', but doesn't mention prerequisites like having a binding_id from governance_bind or how tolerance works. The output schema exists, so return values are presumably covered.

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 baseline is 3. The description does not add extra parameter meaning beyond the schema; it only contextually references 'actual_state' without providing new details.

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 specific purpose: 'Verify that an executed action achieved its declared intent.' It distinguishes itself from sibling tools like 'verify-token' by focusing on outcome verification and explicitly outlining the loop: 'intent -> command -> action -> outcome -> verification.'

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 provides clear context for when to use the tool ('Closes the loop: intent -> command -> action -> outcome -> verification'), implying use after action execution. However, it does not explicitly exclude or compare against alternatives like 'verify' or 'verify-token'.

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

All Kevros — Agentic Identity Trust toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool targets a distinct action or resource: attest creates provenance records, bind declares intent, bundle aggregates evidence, verify checks policy pre-execution, verify-outcome validates results, and verify-token authenticates release tokens. Even the verify-* family is clearly differentiated by timing and purpose.

Naming Consistency4/5

Tool names consistently use lowercase imperative verbs, with hyphenated modifiers for multi-word names (check-peer, verify-outcome, verify-token). The pattern is mostly consistent, though some tools are bare verbs (attest, bind, health) while others include a noun, creating a minor deviation from strict verb_noun style.

Tool Count5/5

Nine tools is well within the ideal range for this domain. Each tool serves a clear purpose in the agentic identity trust lifecycle, from evidence creation to verification and peer assessment, without redundancy or excessive sprawl.

Completeness4/5

The tool surface covers the core workflow: intent binding, policy verification, provenance attestation, outcome verification, token verification, and compliance bundling. Minor gaps exist such as missing explicit revocation or role management, but agents can complete the primary governance lifecycle.

Resources