Skip to main content
Glama

plan_multistep_inquiry

Read-onlyIdempotent

Break complex multilingual customer inquiries into a seven-stage execution plan, extracting order details and enforcing authentication and clarification gates before private lookups or account changes.

Instructions

Deterministically decompose a complex, multi-intent, or code-switched customer inquiry (supporting English, Spanish, Portuguese, French, German, Italian, Dutch, Polish, Banglish, Hinglish, and Spanglish) into a read-before-write 7-stage execution DAG (detect -> plan -> gate -> lookup -> clarify -> verify -> action). Runs completely offline with zero network calls or API key, extracting order IDs, emails, phones, and monetary figures while enforcing identity authentication and clarification gates before state mutations.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "message": "<message>"
    },
    "name": "plan_multistep_inquiry"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesRaw incoming customer message text (single-language or code-switched, single or multi-intent).
localeHintNoFallback ISO language or script hint when no non-English tokens match automatically.en
knownCustomerOrderIdsNoPreviously retrieved order IDs on file for this customer so redundant order-number questions can be skipped.
hasAuthenticatedSessionNoWhether the customer has already completed identity verification for private order/account lookups or mutations.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, closed-world, idempotent, non-destructive; the description adds real value on top by stating it 'runs completely offline with zero network calls or API key', that it is deterministic, and that it enforces authentication and clarification gates. The phrase 'before state mutations' sits alongside readOnlyHint=true but refers to downstream stages rather than this tool writing, so it is ambiguous rather than contradictory. It does not describe the shape of the returned DAG, which is a meaningful gap given there is no output schema.

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?

Two dense sentences with the core action front-loaded in the opening clause; the language list and offline/determinism constraints each carry real information. The parenthetical enumeration of eleven languages is the bulkiest element and could compress, but nothing is pure filler.

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 conceptually heavy tool (multi-language, multi-intent, 7-stage DAG) the description covers input class, supported languages, extraction targets, and gating behavior, and annotations cover the safety profile. The missing piece is what the caller receives and whether it must follow the returned plan, which matters more here because no output schema exists.

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 explains message, localeHint, knownCustomerOrderIds, and hasAuthenticatedSession; the baseline 3 applies. The description adds indirect meaning by pairing 'identity authentication' with hasAuthenticatedSession and 'skipping redundant order questions' with knownCustomerOrderIds, but it adds no format or precedence detail. It also lists Spanglish as supported while the localeHint enum omits it, a small mismatch between prose and schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a precise verb+artifact: 'deterministically decompose' a customer inquiry into a 'read-before-write 7-stage execution DAG', and names the stage sequence. An agent immediately knows this is a planning/decomposition step, not an execution step. It stops short of 5 only because it never names a sibling tool it is not (e.g., octadezx_send_customer_reply or octadezx_verify_order), leaving the routing to inference.

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?

Trigger conditions are explicit: use it for 'complex, multi-intent, or code-switched' inquiries, which tells the agent the input class it applies to. There is no when-not guidance (e.g., simple single-intent messages that could skip planning) and no named alternative, so the caller must infer the boundary itself.

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