Skip to main content
Glama

yeastar_prepare_operation

Read-only

Prepares live PBX operations like phone reboots, batch reprovisioning, agent pause, conference management and call control without executing them, returning a change_id to confirm.

Instructions

PREPARA (non esegue) un'operazione live: riavvio/riprovisioning/modifica batch dei telefoni, login/pausa agenti, gestione conferenze, controllo chiamate. Restituisce un change_id da confermare.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation": "<operation>"
    },
    "name": "yeastar_prepare_operation"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoArgomenti dell'operazione (vedi catalogo)
operationYesNome operazione dal catalogo, es. 'phone_reboot', 'agent_pause', 'call_dial'

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true, which on its own could confuse an agent given the word 'operation'; the description resolves this by stressing that nothing is executed and a change_id must be confirmed. That is genuine added context beyond the structured fields. It does not mention that each call creates a new non-idempotent change (idempotentHint=false) or what happens to unconfirmed changes.

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?

Two sentences, zero filler, with the most decision-relevant fact ('PREPARA, non esegue') capitalized and front-loaded. The return-value clause follows immediately.

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?

With an output schema present and read-only annotations, the description need not explain return values, and it covers staging semantics well. The notable gap is that 'operation' must come from a catalog, and the description does not point to the catalog sibling that enumerates valid operation names.

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 100% and the schema already documents both 'operation' (with examples) and 'args'. The description enumerates operation families that map onto the operation parameter, adding mild orientation, but gives no detail on the 'args' payload shape or the catalog reference. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('PREPARA, non esegue') plus the resource domains it covers (phone reboot/reprovisioning/batch edits, agent login/pause, conference management, call control), and states the outcome (a change_id to confirm). It implicitly separates itself from the apply step, though it never names the sibling tool that performs the confirmation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The parenthetical 'non esegue' plus 'Restituisce un change_id da confermare' tells the agent this is the staging step of a two-phase flow, which is real usage guidance. However, there is no explicit statement of when to prefer it over yeastar_apply_change or the other prepare_* siblings, and no mention of where the operation catalog comes from.

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