Skip to main content
Glama

Approve queued messages

approve_queued_messages
DestructiveIdempotent

Use this when the user has reviewed AI-written messages and wants them sent. Approves up to 100 messages that are waiting for approval: they become scheduled and go out at their time, and a sent message cannot be taken back. Messages that are not waiting for approval are reported as ignored. Free.

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": {
      "sendIds": "<sendIds>"
    },
    "name": "approve_queued_messages"
  }
}

Input Schema

NameRequiredDescriptionDefault
sendIdsYes1 to 100 queued messages, each once, by the `id` the queue lists.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is known. The description adds genuinely new behavioral facts beyond those hints: the batch caps at 100, non-queued IDs are silently reported as ignored rather than erroring, the action is irreversible once sent ("a sent message cannot be taken back"), and it is free. It does not describe the response payload, which is the only notable gap.

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?

Roughly three tight sentences with no filler: trigger condition, effect, edge case, and cost. It leads with the usage trigger rather than the action, which is slightly inverted, and the trailing one-word "Free." is terse but carries real decision-relevant information, so it earns its place.

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 one-parameter mutation with full schema coverage and an annotation set that carries the destructive/idempotent profile, the description covers scope, irreversibility, ignored-input handling, and cost. The one thing an agent cannot learn from either the description or a return schema is what the response looks like (counts, statuses per ID), which keeps this short of a 5.

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 single parameter already documents the array bounds, the 24-char hex pattern, uniqueness, and that IDs come from the queue listing. The description adds only the aggregate "up to 100 messages" framing and qualifies which IDs qualify ("waiting for approval"), which is marginal over the schema. Baseline 3 is appropriate.

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 ("Approves up to 100 messages that are waiting for approval") plus the resulting state change ("they become scheduled and go out at their time"). That is enough to separate it from the decline/edit/skip siblings functionally, but no sibling is named, so differentiation rests on the reader inferring what those other tools do.

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?

Opens with explicit when-to-use guidance: "Use this when the user has reviewed AI-written messages and wants them sent." It also implies the boundary case by stating "Messages that are not waiting for approval are reported as ignored." It stops short of naming an alternative or exclusion (e.g., use decline/edit instead when the user wants changes), so a 4 rather than a 5.

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.

Resources