Skip to main content
Glama
A1 Yandex KIT MCP

A1 Yandex KIT MCP

List customers

list_customers
Read-only

Retrieve paginated store customers and filter by update time for incremental CRM syncs; sort by updated_at so mid-paging changes are not skipped.

Instructions

List customers of the store (paginated), by customer ID ascending by default. updated_from/updated_to filter by last-change time (updated_at) for incremental CRM sync. Sync recipe: updated_from=, sort_by=updated_at, sort_direction=asc, then advance the cursor to the largest updated_at seen — a customer that changes mid-paging moves to the end instead of being skipped, and an all=true run cut off at 500 items resumes from that cursor. Both bounds are inclusive, so the boundary customer comes back on the next poll — deduplicate by customer_id. The response carries a machine-readable coverage envelope (coverage, received, total_count, pages_read); coverage:"partial" MUST be reflected in the user-facing answer and forbids claiming the listing is complete.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_customers"
  }
}

Input Schema

NameRequiredDescriptionDefault
allNoFetch all pages via auto-pagination, up to 500 items; ignores page/per_page.
pageNoPage number, starting at 1 (default 1).
fieldsNoCSV columns; only valid together with format:"csv". Field names are validated against the item schema of the operation's response — an unknown name fails with the list of allowed fields. Default: every top-level scalar field of the item.
formatNoOutput format: "csv" renders the items as RFC 4180 CSV (a leading "# coverage:" comment line, then the header row) instead of JSON — cheaper for wide exports. Default: JSON.
redactNoUse redact:true when the task does not need personal data (e.g. counting or aggregating orders) — personal fields (name, phone, email, date of birth, delivery address and its parts, notes) are replaced with "[redacted]". Applies to the response only; request bodies are never redacted. Default false.
sort_byNoSort field (default "customer_id"). Use "updated_at" for incremental sync.
per_pageNoItems per page, 1-100 (default 25). Values outside the range are clamped.
updated_toNoLatest customer update time, inclusive. RFC 3339 date-time, e.g. "2026-10-02T00:00:00Z".
updated_fromNoEarliest customer update time, inclusive. RFC 3339 date-time, e.g. "2026-10-01T00:00:00Z".
sort_directionNoSort direction (default "asc").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.11.0
    • addedInput schema / properties / sort_by
      Added value: +{
      +  "description": "Sort field (default \"customer_id\"). Use \"updated_at\" for incremental sync.",
      +  "enum": [
      +    "customer_id",
      +    "registered_at",
      +    "updated_at"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / sort_direction
      Added value: +{
      +  "description": "Sort direction (default \"asc\").",
      +  "enum": [
      +    "asc",
      +    "desc"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / updated_from
      Added value: +{
      +  "description": "Earliest customer update time, inclusive. RFC 3339 date-time, e.g. \"2026-10-01T00:00:00Z\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / updated_to
      Added value: +{
      +  "description": "Latest customer update time, inclusive. RFC 3339 date-time, e.g. \"2026-10-02T00:00:00Z\".",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv1.8.0
    • changedInput schema / properties / redact / description
      Previous value: -"Use redact:true when the task does not need personal data (e.g. counting or aggregating orders) — personal fields (name, phone, email, delivery address and its parts, notes) are replaced with \"[redacted]\". Applies to the response only; request bodies are never redacted. Default false."New value: +"Use redact:true when the task does not need personal data (e.g. counting or aggregating orders) — personal fields (name, phone, email, date of birth, delivery address and its parts, notes) are replaced with \"[redacted]\". Applies to the response only; request bodies are never redacted. Default false."
  3. Changed3 schema fields changedv1.6.0
    • addedInput schema / properties / fields
      Added value: +{
      +  "description": "CSV columns; only valid together with format:\"csv\". Field names are validated against the item schema of the operation's response — an unknown name fails with the list of allowed fields. Default: every top-level scalar field of the item.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / format
      Added value: +{
      +  "description": "Output format: \"csv\" renders the items as RFC 4180 CSV (a leading \"# coverage:\" comment line, then the header row) instead of JSON — cheaper for wide exports. Default: JSON.",
      +  "enum": [
      +    "csv"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / redact
      Added value: +{
      +  "description": "Use redact:true when the task does not need personal data (e.g. counting or aggregating orders) — personal fields (name, phone, email, delivery address and its parts, notes) are replaced with \"[redacted]\". Applies to the response only; request bodies are never redacted. Default false.",
      +  "type": "boolean"
      +}
  4. First observedv1.3.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotation already declares readOnlyHint=true, and the description layers substantial extra behavior on top: default ascending customer_id ordering, inclusive bounds that require dedupe by customer_id, mid-paging mutations moving to the end rather than being skipped, and the 500-item cap on all=true. It also discloses the coverage envelope semantics and mandates that coverage:"partial" be surfaced – exactly the kind of non-obvious contract an agent cannot infer.

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 the core purpose and default ordering before the sync recipe, and every sentence carries information (no filler). It is dense and long-ish for a list tool, with several clauses packed per sentence, which costs a bit on readability but not on value.

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, and the description compensates by explaining the coverage/received/total_count/pages_read envelope and the obligation to honor coverage:"partial". For a 10-parameter, zero-required, paginated read tool with a subtle sync contract, nothing an agent needs in order to call and report it correctly is missing.

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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: it explains how updated_from/updated_to compose with sort_by=updated_at as a cursor, that both bounds are inclusive and therefore produce a duplicate boundary record, and how the cursor advances to 'largest updated_at seen'. That is semantic guidance the enum and format strings alone do not convey.

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?

States a specific verb and resource ('List customers of the store'), plus pagination and default ordering, so the agent knows immediately what it returns. It doesn't explicitly separate itself from get_customer or get_customer_orders by name, leaving that differentiation implicit in 'list' vs 'get'.

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 a concrete when-to-use scenario (incremental CRM sync) and the exact recipe, plus the caveat about all=true being cut off at 500 items and how to resume. It doesn't name an alternative tool for a non-incremental read, but within the available sibling set there is no competing list-customers tool, so the guidance is effectively complete.

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