Skip to main content
Glama

yeastar_apply_change

Destructive

Applies a prepared Yeastar PBX configuration change only after explicit user approval, then saves a snapshot, verifies the result, and records it in the audit log.

Instructions

APPLICA al centralino una modifica preparata. Da chiamare SOLO dopo che l'utente ha visto l'anteprima e ha risposto esplicitamente di sì. Se il client lo supporta, il server chiede anche una conferma diretta all'utente (modulo Sì/No) che l'assistente non può compilare al posto suo. Controlla che la configurazione non sia cambiata, salva uno snapshot, esegue, rilegge e verifica, scrive nel registro.

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": {
      "change_id": "<change_id>",
      "confirm": "<confirm>"
    },
    "name": "yeastar_apply_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmYestrue solo dopo che l'utente ha approvato l'anteprima
change_idYeschange_id restituito da una funzione prepare

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already flag destructive=true, non-idempotent and non-read-only, yet the description still adds substantive behavior: a drift check that the configuration has not changed since preparation, an automatic snapshot before executing, a post-execution re-read and verification, and an audit-log entry. It also discloses that a client-side confirmation prompt may appear out-of-band, which the agent must not answer on the user's behalf — none of this is derivable from the annotations.

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 gating condition is front-loaded after the imperative opener, and every clause maps to a distinct fact (precondition, out-of-band confirmation, drift check, snapshot, verify, log). It is dense but not padded; the only mild redundancy is the client-confirmation sentence, which partly overlaps the confirm parameter description.

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 destructive, non-idempotent mutation with an output schema, the description covers preconditions, side effects, and the audit trail without needing to explain return values. Nothing an agent must know to call this safely — sequencing after preview, user consent, irreversibility mitigated by snapshot — is left out.

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 100% and both parameters are self-documenting: confirm is described as valid only after user approval and change_id as the value returned by a prepare function — the description restates essentially the same semantics. With the schema doing the heavy lifting, the baseline 3 applies; the description adds no format, type, or edge-case nuance beyond it.

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?

"APPLICA al centralino una modifica preparata" states a specific verb (apply), a specific target (the PBX), and a specific resource (a previously prepared change). The phrase "modifica preparata" immediately positions it downstream of yeastar_prepare_change and in contrast to yeastar_cancel_change, so an agent can place it in the workflow 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 Guidelines5/5

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

"Da chiamare SOLO dopo che l'utente ha visto l'anteprima e ha risposto esplicitamente di sì" gives an explicit, checkable precondition rather than a vague hint. It also states a hard constraint on the agent's own behavior (the server-side Yes/No form cannot be filled by the assistant), which is exactly the kind of when/when-not guidance an agent needs before a destructive call.

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