Skip to main content
Glama
CTMJSON

ctm-multi-mcp

Official
by CTMJSON

search_calls

Search call records across sub-accounts using filters for date, status, source, and more. Get call outcomes and ad attribution without extra lookups.

Instructions

Search calls across sub-accounts.

Pass account_ids as a comma-separated list, or omit to search all active sub-accounts. For large result sets, use per_page and page for pagination, or use narrow date ranges.

Only searches active sub-accounts by default. Pass account_status="archived", "canceled", "paused", or "all" to search other sub-accounts.

Each result line includes call_status/dial_status, the logged disposition (CTM's 'sale' outcome field, e.g. "wrong number", "no message"), source, tags, and (when present) the ad-platform campaign/keyword from CTM's per-call "paid" attribution object — no need to call get_call just to see the outcome or ad attribution of a call. Note campaign/keyword are frequently blank for non-paid traffic, and keyword specifically can be blank even for paid Search traffic (Google withholds it for some queries) — that omission from the line is expected, not a sign the field is missing from the API.

NOTE: the CTM calls-list API does not reliably filter server-side by status. This tool applies status and disposition as a best-effort client-side filter on top of whatever page is returned, so filtered counts only reflect the current page, not the full unfiltered total shown at the bottom of the output. For an accurate aggregate breakdown across all pages, use call_disposition_report instead of paging through search_calls with a filter.

If what's actually wanted is a row-level list of the matching calls themselves (not just counts) — e.g. "the calls answered over 60s yesterday with ID/Name/City/State" — use call_export instead of paging through search_calls page by page and manually filtering/collecting rows, and instead of looping get_call per call afterward to fill in name/city/state (those fields are already present on every call in this list, no per-call lookup needed). call_export filters across the full date range in one shot and returns ready-to-use CSV.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagNo
pageNo
sortNo
statusNo
user_idNo
end_dateNo
per_pageNo
queue_idNo
caller_idNo
source_idNo
contact_idNo
start_dateNo
account_idsNo
dispositionNo
account_statusNo
tracking_number_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations, the description fully discloses behavioral quirks: server-side filtering is unreliable for status so client-side filtering is best-effort and page-limited; only active sub-accounts are searched by default; campaign/keyword may be blank for non-paid or withheld by Google. These are critical non-obvious behaviors.

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 long but every sentence contributes essential guidance. It is well-structured into focused paragraphs (scope, pagination, filtering limitation, alternative tools), and the content density justifies the length. No filler or redundancy.

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?

For a complex search tool with 16 optional parameters, no annotations, and no schema descriptions, this description covers almost everything an agent needs: result contents, filtering limitations, expected blanks, pagination, and when to use sibling tools. The presence of an output schema means return-value details are not required here.

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?

Although the schema has zero descriptions for its 16 parameters, the description adds significant meaning for key ones: account_ids, account_status, page/per_page, status/disposition, and date ranges. However, some parameters like sort, user_id, queue_id, and tracking_number_id are not explicitly explained, so coverage is not complete.

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 description clearly states the tool's purpose: 'Search calls across sub-accounts' and expands on the specific result fields (call_status/dial_status, disposition, source, tags, campaign/keyword) that distinguish it from siblings like get_call and call_export. This makes the tool's role unmistakable.

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?

Excellent guidance: it explicitly recommends call_disposition_report for accurate aggregate counts, call_export for row-level lists, and notes that per-call outcome/ad attribution is already present so there is no need to call get_call afterward. It also explains account_status options and pagination strategy.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CTMJSON/ctm-multi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server