Skip to main content
Glama
AIops-tools

fabric-aiops

by AIops-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

aci_endpoint_trace

Read-only

Reconstruct an ACI endpoint's static fabric path from MAC or IP to attachment, EPG, bridge domain, VRF, contracts, filters, and related fault candidates.

Instructions

[READ] Reconstruct an ACI endpoint's static fabric path from its MAC or IP.

One call follows: endpoint → attachment (pod / leaf / interface or vPC) →
EPG → bridge domain → VRF → contracts the EPG provides/consumes → filter
entries, plus faults whose DN names the EPG or the attachment interface.
Every link is the relation APIC resolved (its tDn), so cross-tenant links
into 'common' are followed correctly.

How to read the result (do not over-state it):
  * It is NOT a reachability test. 'staticPathResolved: true' means the
    fabric is configured to carry the endpoint, not that traffic flows.
  * 'relatedFaultCandidates' are matched by DN only — proximity, not cause.
    Never report one as the reason for a problem. 'faults: null' means no
    fault scan succeeded (related faults unknown, not none); 'complete:
    false' means some scan failed, hit its page limit, or could not run.
  * 'tagRelations' in state 'missing-target' are policy-tag lookups and say
    nothing about the attachment path; do not report them as a path failure.
  * A section that is null with an entry in 'errors' was NOT read — never
    describe it as empty or absent. 'segmentResolved'/'staticPathResolved'
    are null in that case, not false.
  * A cleared fault keeps the description it had when raised; judge it by
    severity/lifecycle, not by its text.
  * 'contracts.complete: false' means a contract or filter was not read or
    not returned (its entry says 'read: false', 'exists: false' or has
    'entries: null') — its rules are unknown, not absent. The EPG → BD →
    VRF verdict is unaffected.
  * An 'epg' with 'supported: false' is a parent object this read does not
    trace (e.g. an L2Out external EPG) — the chain is undetermined, not broken.
  * 'notFound' means the fabric has not learned the address now, or it is in
    a tenant this account cannot see — not that the host is down.
  * 'notChecked' lists what this read does not evaluate (vzAny, taboo
    contracts, imported contracts, preferred-group peers, service graphs).

Args:
    mac: Endpoint MAC (any case; e.g. 00:50:56:AB:CD:EF). Pass mac OR ip.
    ip: Endpoint IPv4/IPv6 address. Pass mac OR ip.
    limit: Max matching endpoints to trace (default 5, max 20); the result
        carries returned/limit/truncated.
    fault_limit: Max related-fault candidates per endpoint (default 20).
    target: Target name from config (must be 'platform: aci').

endpoint.recordedPathMatch compares APIC's fabricPathDn with the formed
attachment: "exact", "vpc-member" (APIC records a vPC-learned endpoint on one
member leaf, e.g. paths-301 for protpaths-301-302 — the same attachment, not
a move), "differs" (a medium finding that does not claim a move), or null (no recorded
path, or no formed relation — not compared; never a match). Paths behind a FEX
are not excused as vPC members.

Returns dict: {query, endpoints:[{endpoint, ips, attachment, attachmentFormed,
    tagRelations, epg, bd, vrf, contracts, segmentResolved, notChecked,
    relatedFaultCandidates, staticPathResolved, findings:[{rank, severity,
    signal, cause, action}], errors}], returned, limit, truncated,
    serverReportedMatches, lookupErrors, note, notFound?}.

Input Schema

NameRequiredDescriptionDefault
ipNo
macNo
limitNo
targetNo
fault_limitNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.12.0

TDQS

A4.7/5.0
Behavior5/5

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

With readOnlyHint already covering safety, the description goes far beyond annotations: it explains null-vs-error semantics, 'complete: false' meaning partial reads, 'notFound' semantics, 'tagRelations' missing-target interpretation, FEX/vPC path matching, and what the read deliberately does not evaluate (notChecked). This is unusually rich behavioral disclosure for a read tool.

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 [READ] and the one-line purpose, then organized into labelled bullet blocks for result interpretation. It is long, but nearly every bullet addresses a distinct misreading risk; the only cost is bulk, not filler.

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?

There is no output schema, yet the description enumerates the return dict shape (query, endpoints[...], findings, errors, returned/limit/truncated, notFound) and explains the meaning of the ambiguous fields. Given the complexity of the traversal, this is complete enough for an agent to call and interpret it.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden — and it does: all five params are documented, including case-insensitivity and MAC example, mac-XOR-ip exclusivity, limit default 5/max 20 plus the returned/limit/truncated result fields, fault_limit default 20, and the target value constraint 'platform: aci'.

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?

[READ] plus a specific verb ('Reconstruct') and resource ('ACI endpoint's static fabric path'), scoped to MAC or IP input. The enumerated chain (endpoint → attachment → EPG → BD → VRF → contracts → filters) makes the operation concrete and distinguishable from siblings like aci_faults_list or aci_epg_segment.

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?

Gives clear calling conditions ('Pass mac OR ip') and strong scope exclusions, most importantly that it is NOT a reachability test and that fabric path resolution is not traffic flow. No sibling tool is named as an alternative (e.g. aci_faults_list for raw faults), leaving the routing implicit.

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

Deploy Server

Other Tools