Skip to main content
Glama

SAGOT

by com.sagots
OverviewDiscussionsAdmin

calls_create

Queue one call with an agent to a contact. Give task for what this one call must achieve (the personal starter agent follows it). During the alpha a line only calls its test numbers, unless it is a SAGOT number line in live mode. Calls on SAGOT numbers reserve their maximum cost from the prepaid balance (BALANCE_TOO_LOW, SPEND_LIMIT_REACHED, COUNTRY_NOT_SUPPORTED). When an AI assistant connected by OAuth asks for a call and the policy's assistantCallApproval is on (default), the call is created with status awaiting_approval and nothing dials until a person approves it on the website: tell them, and give them the returned approvalUrl. It is canceled if not approved within 24 hours. Then read the result with calls.get.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskNoWhat this one call must achieve, in plain words — e.g. 'Ask for a table for 4 on Friday 18 Oct at 7pm under Cruz; 7–8pm is fine; no deposit.' Given to the agent beneath its instructions.
draftNo
lineIdNo
agentIdYes
contactIdYes
workspaceIdYes
idempotencyKeyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / task
      Added value: +{
+  "description": "What this one call must achieve, in plain words — e.g. 'Ask for a table for 4 on Friday 18 Oct at 7pm under Cruz; 7–8pm is fine; no deposit.' Given to the agent beneath its instructions.",
+  "maxLength": 1000,
+  "type": "string"
+}
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: cost reservation from prepaid balance with named error codes (BALANCE_TOO_LOW, SPEND_LIMIT_REACHED, COUNTRY_NOT_SUPPORTED), the awaiting_approval gate and its 24-hour auto-cancel, and the returned approvalUrl to surface to the user. These are non-obvious behaviors an agent must know before calling.

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-loads the core action and each sentence adds useful behavior (task, alpha restriction, cost/errors, approval flow, follow-up). It is dense and slightly run-on, but no sentence is wasted.

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?

For a creation tool with no output schema and no annotations, it covers the key behavioral consequences (queuing, cost reservation, possible approval gate) and points to calls.get for the result. It leaves idempotency and the draft parameter unexplained, which are minor gaps given how much else is covered.

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 coverage is only 14%, so the description must compensate. It explains `task` well and hints at `lineId` behavior via test-number/SAGOT semantics, but says nothing about idempotencyKey, draft, or the required workspaceId/agentId/contactId beyond inferable names. Partial compensation only.

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?

States a specific verb and resource ('Queue one call with an agent to a contact') and clarifies the task parameter's intent. It is clearly distinguishable from siblings like calls_approve, calls_cancel, and campaigns_start without opening any schema.

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 concrete use conditions: alpha lines only dial test numbers unless a SAGOT line in live mode, and OAuth assistant calls may be gated by assistantCallApproval. It also routes the follow-up read to calls.get. It does not explicitly contrast against siblings like campaigns_start, so not a full 5.

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

All SAGOT toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources