Skip to main content
Glama
CTMJSON

ctm-multi-mcp

Official
by CTMJSON

call_export

Export filtered call records as CSV with custom fields, date ranges, and status/source filters. Get reliable row-level call data across dates without per-call API loops.

Instructions

Export a filtered, row-level list of individual calls as CSV.

Use this — not search_calls, not a get_call loop — any time the ask is for actual call records matching a filter (e.g. "answered calls over 60s yesterday with ID/Name/City/State", "give me the calls from Google Ads last week with caller number and city"). It replaces two things people otherwise reach for and both are worse:

  1. Paging through search_calls with a status/disposition filter — that tool only filters within whatever single page it fetched, not across the full date range, so a "321 matching calls" answer from paging is unreliable; the total at the bottom of search_calls output is always the unfiltered count.

  2. Looping get_call once per matching call to read name/city/state — unnecessary. CTM's calls-list endpoint already returns name, city, and state on every call record; this tool fetches once (paginated server-side, same mechanism as call_disposition_report and call_crosstab) and reads those fields directly off the already-fetched payload. No per-call round trip.

Filters (all optional, AND together): min_duration/max_duration (seconds), status (matches call_status/status/dial_status, exact, case-insensitive — e.g. "answered"), source (substring match against the marketing source name, case-insensitive). These are applied client-side across the entire fetched set (bounded by max_calls), not per-page — this is what makes the count reliable, matching what call_disposition_report would report for the same filters. Cross-check against call_disposition_report's "Calls analyzed" count if you want a sanity check before trusting the row count here.

fields: comma-separated columns, in order, forming the CSV header. Supported: id, source, name, city, state, called_at, duration, status, dial_status, disposition, caller_number, tracking_number, receiving_number, agent, tag, day_of_week, campaign, campaign_id, keyword, ad_group, ad_group_id, medium, ad_network, ad_match_type, paid_source. The last several are CTM's per-call "paid" ad-attribution fields (see call_crosstab's docstring for caveats about campaign/keyword sometimes coming back "(not provided)").

sort: field to order rows by, prefix "-" for descending (default "-called_at", most recent first). Only "called_at" and "duration" are supported as sort keys; anything else leaves rows in fetch order.

Use start_date/end_date (ISO format) or time_duration (e.g. 'today', 'yesterday', 'wtd', 'last7days' — see call_crosstab's docstring for the full list of accepted values).

Returns raw CSV text — header row plus one row per matching call. Hand it straight to the user as a file, or paste into a spreadsheet. Rows are capped at max_calls fetched per account (raise it for high-volume accounts/date ranges); a truncation warning is included as a leading comment line if any account hit the cap.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNo-called_at
fieldsNoid,source,name,city,state,called_at,duration
sourceNo
statusNo
end_dateNo
max_callsNo
start_dateNo
account_idsNo
max_durationNo
min_durationNo
time_durationNo
account_statusNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations present, the description fully discloses the tool's behavior: it returns raw CSV text with a header row, applies filters client-side after fetching the entire bounded set, includes a truncation warning as a leading comment if max_calls is hit, and uses server-side pagination through the same mechanism as call_disposition_report. It also warns about the unfiltered count in search_calls output, which is important for interpreting results.

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 front-loaded: it opens with a clear one-sentence purpose, then organizes information into paragraphs for alternatives, filters, fields, sort, dates, and return value. Every paragraph adds essential behavioral or usage detail, and the structure (with explicit 'Filters', 'fields:', 'sort:' labels) makes it easy to scan.

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 12-parameter tool with no annotations, this description is exceptionally complete: it covers the return format, edge cases (truncation warning), cross-tool sanity checks (call_disposition_report), and the exact list of supported fields. It even explains the pitfalls of using sibling tools, which helps an agent avoid misuse.

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?

The schema has zero parameter descriptions, so the description is critical. It meticulously documents most parameters: filters (min/max_duration, status, source), fields (with a full supported list and semantics), sort (with allowed keys and default), date/time selectors (start_date/end_date or time_duration), and max_calls (with the cap behavior). However, account_ids and account_status are not explicitly explained, leaving a small gap despite the otherwise thorough coverage.

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 first sentence clearly states the tool exports a filtered, row-level list of calls as CSV, naming the specific verb and output format. It explicitly differentiates from siblings by saying 'not search_calls, not a get_call loop', and clarifies the use case with examples.

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 extensive guidance: it tells the agent to use this tool when raw call records matching a filter are needed, and explicitly names two tempting alternatives (search_calls and get_call) that are worse. It explains why those alternatives fail (per-page filtering and per-call loops) and even gives example queries, making the when-to-use decision unambiguous.

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