Skip to main content
Glama

Call For Me

by io.github.kimjin8

place_call

Place an outbound phone call to a US business or person. The A.I. assistant on the call will identify itself as A.I., follow your instructions, and return a structured outcome via get_call_status.

USE THIS TOOL WHEN: the user wants to make a phone call, contact a business by phone, ask about hours/pricing/availability, book a reservation, gather info that's not online, follow up on a service request, or do any task that requires talking to a human on the phone.

LIMITATIONS:

  • US phone numbers only (E.164 starting with +1). International is not yet supported.

  • English language only.

  • Cannot call emergency services (911, 988, etc.) — these will be rejected.

  • The A.I. will NOT commit to bookings/payments without user confirmation unless safety.must_confirm_with_user is explicitly set to false.

  • Default 5-minute call duration cap.

Returns immediately with a call_id. Poll get_call_status(call_id) for the result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
userYes
safetyNo
targetYes
instructionsYesThe conversation goals/script the AI should follow. Agent owns this. We wrap it with mandatory safety layer (disclosure, hangup, voicemail, graceful-exit rubric). Be specific — what to ask, what tone, what to do if recipient declines.
output_schemaNoJSON Schema for the structured outcome you want extracted from the transcript.
idempotency_keyYes

TDQS

A4.4/5.0
Behavior4/5

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

No annotations provided, so description carries full burden. It discloses AI identity, structured outcome via get_call_status, call duration cap, and restrictions. Could add more on error handling or rate limits, but covers key 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?

Description is well-structured with sections and bullet points, no wasted sentences. Each line adds value, from purpose to limitations to output pattern.

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?

Covers purpose, limitations, output pattern (call_id + poll), and mentions sibling tool. Given 6 parameters and no output schema, slightly more detail on safety settings or output_schema parameter could improve, but overall complete.

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 33%, so description must compensate. It mentions 'instructions' and 'output_schema' and explains the return flow, but does not detail 'user', 'target', or 'safety' parameters beyond schema. Adequate but not rich.

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 verb 'Place' and the resource 'an outbound phone call to a US business or person', and distinguishes from sibling 'get_call_status' which is for polling results.

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?

Explicitly lists usage scenarios with 'USE THIS TOOL WHEN:' and includes limitations (US only, English, no emergency calls, commitment rules). Clearly separates when to use this vs. polling with sibling.

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

All Call For Me toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: place_call initiates a call and returns an ID, while get_call_status polls for the outcome. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools use consistent snake_case with a verb_noun pattern (place_call, get_call_status), making the convention predictable and easy to follow.

Tool Count4/5

With only two tools, the set is minimal but well-scoped for the core workflow of placing a call and checking its status. It is slightly undercounted but reasonable for this narrow domain.

Completeness4/5

The tools cover the essential call lifecycle (place and poll status). A minor gap is the lack of a cancel or list calls feature, but the core task is fully supported.

Resources