CallRail MCP

by pghdma

Overview Schema Source Related Servers Discussions Admin

Python

Remote

bulk_update_calls

Apply the same update to every call matching a filter.

Instructions

Apply the same update to every call matching a filter.

Useful for: "tag every Bing call this month as low-priority", "mark all <30s unanswered calls from this number as spam", "add a note to every call from a specific landing page". Replaces dozens of sequential update_call invocations with one tool call.

Safety: dry_run=True by default, so this tool returns a preview of which calls WOULD be updated without actually writing. Pass dry_run=False to commit. Hard cap of 500 calls per invocation to prevent runaway bulk operations.

Args: company_id, days: filter (same semantics as list_calls). At least one filter must be provided to avoid "update everything ever". answer_status: server-side filter. One of 'answered', 'missed', or 'voicemail'. answered: DEPRECATED alias ('true' -> answered, 'false' -> missed). Before v1.2.0 this was forwarded as an answered query param that CallRail does not implement: the filter was silently dropped, so a commit run updated EVERY call in the window. source: applied CLIENT-SIDE (exact, case-insensitive match on each call's source field) because CallRail has no server-side source filter. Matching happens before the 500-cap is applied. set_tags_add: tag names to ADD to each matched call (preserves existing tags). Mutually compatible with other set_* fields. set_note: note text to set on each matched call (replaces existing). set_lead_status: e.g. 'good_lead', 'not_a_lead'. set_spam: True to mark spam. NOTE: CallRail does not support un-marking spam via the API, so set_spam=False is rejected. dry_run: If True (default), return preview only. False = commit. account_id: Auto-resolves if omitted.

Returns: - If dry_run: {"dry_run": true, "matched": N, "would_update_calls": [...], "set_fields": {...}} - Else: {"dry_run": false, "matched": N, "updated": M, "failed_count": K, "failures": [...]}

Performance note: when set_tags_add is used, the commit phase issues 1 extra GET per call to fetch fresh tags before merging (race protection against concurrent tag writes). For a max bulk of 500 calls, this is ~2× the latency vs other set_* fields. Other update fields (note, lead_status, spam) skip the extra GET.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No
`source`	No
`dry_run`	No
`answered`	No
`set_note`	No
`set_spam`	No
`account_id`	No
`company_id`	No
`set_tags_add`	No
`answer_status`	No
`set_lead_status`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.2.2Sep 14, 2026

addedInput schema / properties / answer_status

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Answer Status"
+}

First observedv1.0.0Apr 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full burden. It discloses the safety default (`dry_run=True`), the 500-call hard cap, client-side vs server-side filtering, race protection with extra GETs, and the non-reversible spam marking. It also details the deprecated `answered` parameter's historical failure mode. This is exemplary transparency beyond any annotation coverage.

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?

The description is lengthy but each section earns its place: motivation, safety, parameter semantics, return format, performance note. It is front-loaded with the core purpose and safety. Slight redundancy exists (e.g., repeating the 500-cap in the performance note and safety section), but the structure is clear with headings. It could be tightened slightly but is well organized.

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?

Given 11 parameters, zero schema coverage, no annotations, and an output schema that only partially covers return values, the description provides everything needed: parameter semantics, defaults, side effects, failure modes, performance implications, and return format. It is complete for an agent to invoke correctly without additional context.

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 0%, so the description must fully explain each parameter. It does: `company_id` and `days` are tied to `list_calls` semantics, `answer_status` is a server-side filter with enumerated values, `answered` is deprecated alias with a historical caveat, `source` is applied client-side, all `set_*` fields are explained with behavior (add vs replace), `dry_run` default, and `account_id` auto-resolution. It also documents the return object structure. This is comprehensive and compensates completely for missing schema descriptions.

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 a specific verb ('Apply the same update to every call matching a filter'), the resource ('calls'), and the scope of operation. It provides concrete examples and distinguishes it from the sequential `update_call` tool, which is its primary sibling. The purpose is unmistakable and well differentiated.

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 explicitly explains when to use this tool: for bulk operations 'Replaces dozens of sequential `update_call` invocations with one tool call.' It also provides negative guidance: 'At least one filter must be provided to avoid "update everything ever"' and warns about the `answered` deprecation. Alternatives are referenced (`list_calls`, `update_call`). This is thorough and actionable.

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

Deploy Server