AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks

Check Agent Trust

check_agent_trust

Read-onlyIdempotent

Pre-invocation trust check for an unknown AI agent or MCP server endpoint. Read-only, requires no AgentTrust API key or account. Looks up an agent by its exact invocation URL among AgentTrust's already-observed public agents and returns its status, endpoint-ownership verification, agent reliability score (when available), and a machine-readable trustDecision (recommended, confidence, reasons). Does NOT contact endpointUrl itself during this check — it only reads AgentTrust's own existing monitoring history. An unregistered URL returns { matched: false }, never an error.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`endpointUrl`	Yes	The exact invocation URL of the agent you're about to call. Used only to look up AgentTrust's own already-observed data for it — this endpoint is never contacted during the check.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No
`slug`	No
`status`	No
`matched`	Yes
`verified`	No
`trustDecision`	No
`reliabilityScore`	No
`reliabilityScoreStatus`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 26, 2026

addedOutput schema / properties / reliabilityScoreStatus

Added value: +{
+  "enum": [
+    "none",
+    "fresh",
+    "stale"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 21, 2026

addedInput schema / properties / endpointUrl / description

Added value: +"The exact invocation URL of the agent you're about to call. Used only to look up AgentTrust's own already-observed data for it — this endpoint is never contacted during the check."

AddedSep 19, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds high-value behavior beyond them: it does NOT contact endpointUrl during the check (only reads AgentTrust's own monitoring history), and an unregistered URL returns { matched: false } rather than an error. These are exactly the runtime expectations an agent needs.

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?

Every sentence carries unique information — purpose, auth requirements, lookup semantics, non-contacting behavior, and the error-free miss case. It is front-loaded with the purpose and has no filler or repetition.

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?

For a single-parameter, read-only lookup with an output schema, the description covers invocation context, auth, no-side-effect guarantees, and the negative-result shape. Nothing material is left for the agent to infer.

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% and the single parameter is already documented in the schema, so the baseline is 3. The description meaningfully reinforces that the URL must be the exact invocation URL and clarifies its role (lookup key only, never contacted), adding a bit of meaning beyond the schema text.

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 and resource ('Pre-invocation trust check', 'looks up an agent by its exact invocation URL') and enumerates what is returned (status, ownership verification, reliability score, trustDecision). The read-only, lookup-only nature distinguishes it from siblings like get_agent and get_agent_health, which operate on already-known agents.

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?

Clearly scopes usage to 'an unknown AI agent or MCP server endpoint' before invocation, and states it needs no API key or account, which tells the agent it can be called freely. It does not explicitly name or compare against the sibling tools, so it stops short of explicit alternative routing.

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

All AgentTrust — Pre-Invocation AI Agent Trust & Reliability Checks 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.