Skip to main content
Glama

Agent Broker

by io.github.basilalshukaili

handle_inbound

Classify an inbound message on behalf of an SMB and get a recommended next action. Classifies intent (booking request, cancellation, opt-out, inquiry, complaint) and returns a suggested_action for YOUR agent to act on - opt-outs are recorded durably; nothing else is auto-routed or auto-executed by this tool.

EXAMPLE USER QUERIES THAT MATCH THIS TOOL: user: "Process this customer reply for me: 'Yes I want to book Tuesday'" -> call handle_inbound({"smb_id": "smb_xyz", "inbound_channel": "sms", "raw_message": "Yes I want to book Tuesday"})

WHEN TO USE: Use when an SMB needs inbound message triage — classifying incoming contact-form submissions, SMS replies, voicemails, or email inquiries. WHEN NOT TO USE: Do not use for outbound communications. Do not use for compliance-flagged recipient lists without verified opt-in records. COST: $0.03 per_call LATENCY: ~3000ms EXECUTION: async_by_default (use get_outcome to retrieve result)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
senderNo
smb_idYes
raw_messageYes
routing_rulesNoOptional override routing policy for this SMB
idempotency_keyNoOptional client-supplied key for safe retries. Replaying the same key within 24h returns the original receipt - the operation is NOT re-executed and NOT re-charged.
inbound_channelYes
received_at_isoNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional client-supplied key for safe retries. Replaying the same key within 24h returns the original receipt - the operation is NOT re-executed and NOT re-charged.",
+  "maxLength": 128,
+  "type": "string"
+}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only provide generic hints (readOnlyHint=false, idempotentHint=false), so the description carries the behavioral burden. It discloses that opt-outs are recorded durably, no other action is auto-executed, execution is async by default, results must be retrieved via get_outcome, and it adds cost and latency details. This is strong context beyond what annotations and schema provide.

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 well-structured with clear headings, front-loads the core purpose, and uses a runnable example that earns its place. Cost, latency, and execution mode each get a single concise line, and no content feels redundant with the schema.

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?

For a tool with no output schema and seven parameters, the description covers required call shape, intents, use cases, exclusions, async result retrieval, and operational characteristics. The main gap is the lack of detail about the exact shape or possible values of suggested_action beyond the intent list, but the definition is sufficient for safe invocation.

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 description coverage is only 29%, but the description compensates with a concrete example call that maps a natural-language request to the three required parameters: smb_id, inbound_channel, and raw_message. The WHEN TO USE section also clarifies channel semantics. Optional parameters like sender and received_at_iso are left to self-evident names and schema structure, so it is helpful but not exhaustive.

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 opening sentence states a specific verb-resource pair ('Classify an inbound message on behalf of an SMB') and defines the output ('recommended next action'), while explicitly listing the intents it handles. It also distinguishes itself from send-style tools by noting that nothing is auto-routed or auto-executed except durable opt-out recording.

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?

The description provides explicit WHEN TO USE and WHEN NOT TO USE sections, naming concrete inbound contexts (contact forms, SMS replies, voicemails, emails) and exclusions (outbound communications, compliance-flagged recipient lists without verified opt-in records). This gives an agent direct decision criteria without needing to inspect sibling tools.

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

All Agent Broker 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

A4.2/5.0
Disambiguation4/5

Most tools have clearly differentiated targets (e.g., check_booking_link vs import_booking_url, get_status vs get_outcome), and the descriptions are unusually thorough. However, send_message and send_transactional_confirmation overlap because send_message already includes a 'transactional' message type, and verify_business vs verify_company_record are easy to confuse despite different scopes.

Naming Consistency5/5

All 23 tools use a consistent verb_noun snake_case pattern (check_*, get_*, send_*, verify_*), with no camelCase or stylistic drift. The verb uniformly precedes the object, making the surface predictable and easy to navigate.

Tool Count3/5

23 tools is on the heavy side for a single MCP server, spanning SMB communications, booking, compliance screening, trade lookup, and platform utilities. Each tool has a purpose, but the count pushes the set into the 16-25 borderline range and suggests scope creep.

Completeness3/5

Core workflows for booking, messaging, and compliance pre-flight are well covered, including async polling and cost preview. However, there are lifecycle gaps: capture_lead has no way to list/update/retrieve leads, and business records support import/verify but no update/delete. The trade/company-verification tools also feel disconnected from the main SMB flow.

Resources