Skip to main content
Glama

Message: Edit

message_edit
Destructive

Edit one previously sent message where supported. Recommended chain: resolve chat -> list messages -> message_get -> edit. Keep exact chat_id + message_id pair. Chat ID: Exact provider chat/conversation ID. LinkedIn chat IDs may also be visible in /messaging/thread/{chat_id}/ URLs. Obtain with: provider list conversations/inbox chats -> chat.id Never pass: person name, user_id, message_id. Message ID: Exact message id inside a specific chat. In V2 always keep chat_id together with message_id because providers may only guarantee uniqueness inside the chat. Obtain with: provider read/list conversation messages -> message.id Never pass: message text, chat_id, message ID without its chat context for mutation tools.

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": {
      "chat_id": "<chat_id>",
      "message_id": "<message_id>",
      "text": "<text>"
    },
    "name": "message_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesFinal replacement message text explicitly requested/approved by the user.
chat_idYesExact chat/conversation ID from a conversation/chat listing or resolver. A person name/user_id is NOT a chat_id. Chat ID: Exact provider chat/conversation ID. LinkedIn chat IDs may also be visible in /messaging/thread/{chat_id}/ URLs. Obtain with: provider list conversations/inbox chats -> chat.id Never pass: person name, user_id, message_id.
account_idNoOptional Nilyo connection ID (unipile_account_id from list_connected_accounts). Omit when the user has one account for this provider. When several exist, Nilyo never guesses: list them (display name, identifier, provider user ID), choose the one the user named or ask, and pass its ID here.
message_idYesExact message ID returned inside the specified chat. Keep it paired with chat_id for all V2 message mutations/reactions. Message ID: Exact message id inside a specific chat. In V2 always keep chat_id together with message_id because providers may only guarantee uniqueness inside the chat. Obtain with: provider read/list conversation messages -> message.id Never pass: message text, chat_id, message ID without its chat context for mutation tools.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is handed to the agent. The description adds two useful facts beyond that: edits are only possible 'where supported' by the provider, and the text must be explicitly user-approved. It never says the previous message body is overwritten and unrecoverable, or what happens when editing is unsupported.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core instruction and the call chain are front-loaded, which is good, but a large share of the body duplicates the schema's parameter descriptions word for word. The two ID glossaries could be collapsed to a single line each without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutation with no output schema, the description covers ID sourcing and sequencing adequately. Gaps remain around what the tool returns after an edit, provider-specific support limits, and failure behavior, which matter for a destructive, non-idempotent operation.

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%, so every parameter including account_id is already documented in the schema. The description's chat_id/message_id paragraphs are essentially verbatim copies of the schema text, so they add explanation value but not new meaning beyond structured data. 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?

States a specific verb and resource ('Edit one previously sent message'), which clearly separates it from message_send, message_delete and message_forward in the sibling list. The 'where supported' qualifier hints at provider limitations but never names which providers or what the limitation is.

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 an explicit recommended call chain (resolve chat -> list messages -> message_get -> edit) plus concrete acquisition paths for both IDs, which is real when-to-use guidance. It does not state when an edit should be refused or when to prefer delete + resend, so the exclusions side is thin.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.