NAIF Agent Gravity — MCP Diagnostics & Recovery

Diagnose Issue

diagnose_issue

Start here. Diagnose one sanitized MCP, API, webhook, agent or integration failure for free. Returns bounded evidence plus a suggested repair service, then use quote_repair only if a priced repair is wanted. It never creates a quote, checkout, payment or repair job. It may record bounded operational attribution/telemetry, so readOnlyHint is false; it does not modify the caller system or commercial state.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`source`	No	Optional attribution label for the calling agent or integration; omit when no stable source label is available.
`problem`	Yes	One sanitized technical symptom. Include the affected component and observable error/status. Never include secrets, credentials, private keys or PII.

Output Schema

TableJSON Schema

Name	Required	Description
`free`	No	True for this free diagnostic step.
`error`	No	Present when a bounded diagnosis could not be produced.
`phase`	No	DIAGNOSE on a successful bounded diagnosis.
`nextTool`	No	quote_repair when the caller wants a priced bounded repair.
`automaticQuote`	No	False; diagnosis never creates a quote automatically.
`rawInputStored`	No	False when the raw diagnostic input is not retained as payload data.
`automaticPayment`	No	False; diagnosis never sends or charges payment.
`automaticCheckout`	No	False; diagnosis never creates checkout automatically.
`automaticExecution`	No	False; diagnosis never starts repair execution.
`suggestedProductId`	No	Public repair product suggested from the diagnosis when available.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 5, 2026

changedInput schema / properties / problem / description

Previous value: -"One sanitized technical symptom. Never include secrets, credentials, private keys or PII."New value: +"One sanitized technical symptom. Include the affected component and observable error/status. Never include secrets, credentials, private keys or PII."

changedInput schema / properties / source / description

Previous value: -"Optional attribution label."New value: +"Optional attribution label for the calling agent or integration; omit when no stable source label is available."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Bounded diagnosis result. On success phase is DIAGNOSE and nextTool is quote_repair; an error field indicates diagnosis was unavailable.",
+  "properties": {
+    "automaticCheckout": {
+      "description": "False; diagnosis never creates checkout automatically.",
+      "type": "boolean"
+    },
+    "automaticExecution": {
+      "description": "False; diagnosis never starts repair execution.",
+      "type": "boolean"
+    },
+    "automaticPayment": {
+      "description": "False; diagnosis never sends or charges payment.",
+      "type": "boolean"
+    },
+    "automaticQuote": {
+      "description": "False; diagnosis never creates a quote automatically.",
+      "type": "boolean"
+    },
+    "error": {
+      "description": "Present when a bounded diagnosis could not be produced.",
+      "type": "string"
+    },
+    "free": {
+      "description": "True for this free diagnostic step.",
+      "type": "boolean"
+    },
+    "nextTool": {
+      "description": "quote_repair when the caller wants a priced bounded repair.",
+      "type": "string"
+    },
+    "phase": {
+      "description": "DIAGNOSE on a successful bounded diagnosis.",
+      "type": "string"
+    },
+    "rawInputStored": {
+      "description": "False when the raw diagnostic input is not retained as payload data.",
+      "type": "boolean"
+    },
+    "suggestedProductId": {
+      "description": "Public repair product suggested from the diagnosis when available.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedOct 5, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The description reconciles an otherwise confusing annotation by explaining that bounded operational attribution/telemetry is recorded, hence readOnlyHint=false, while asserting it does not modify the caller system or commercial state. It leaves the non-idempotent hint unexplained (repeat calls likely duplicate telemetry) and gives no failure/rate-limit behavior, so it is strong but not exhaustive beyond the 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?

Four short sentences, front-loaded with the routing instruction ('Start here'), then deliverable, then sibling routing, then side-effect disclosure. No filler; each sentence carries decision-relevant information.

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?

With an output schema present, return values need not be described, and the description still summarizes the response shape. Safety, routing and side effects are covered; the only gap is repeated-call/idempotency behavior for a tool annotated non-idempotent.

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 both parameters including the sanitization and maxLength constraints. The description reinforces 'one sanitized technical symptom' but adds no new syntax or format guidance beyond that baseline.

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 (diagnose) and resource (one sanitized MCP/API/webhook/agent/integration failure), plus the scope limit 'one ... for free' and the concrete deliverable ('bounded evidence plus a suggested repair service'). It explicitly distinguishes itself from quote_repair, so an agent can route without opening either 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?

'Start here' establishes it as the entry point, and 'then use quote_repair only if a priced repair is wanted' names the alternative and the exact condition that selects it. Negative guidance is also explicit: it never creates a quote, checkout, payment or repair job, which rules out the downstream siblings.

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

All NAIF Agent Gravity — MCP Diagnostics & Recovery tools Inspect

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.