Skip to main content
Glama

Request Letter Send

request_send
Destructive

Request that a draft be mailed.

approval-tier keys: creates a PENDING request and returns a one-tap Allow/Deny approval_url for the human. Nothing is mailed until Allow. on_command keys: may auto-send inside guardrails (spend caps, content screening, anomaly detection); anything outside them stays PENDING.

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": {
      "api_key": "<api_key>",
      "draft_id": "<draft_id>"
    },
    "name": "request_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
api_keyYesyour 3L-Group Technology API key (lms_...).
draft_idYesthe draft_id returned by draft_letter.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Goes well beyond the annotations by spelling out the two execution modes: approval-tier calls create a PENDING request with a one-tap approval_url, and nothing is mailed until Allow arrives. For on_command keys it discloses auto-send guardrails (spend caps, content screening, anomaly detection) and what happens when those guardrails are crossed. This is exactly the kind of side-effect detail a destructive, non-idempotent tool needs.

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 core action is stated in the first line, then the two behavioral branches are separated cleanly with labeled prefixes, so it is easy to skim. Slightly hurt by broken line wrapping mid-sentence and by referencing 'approval-tier'/'on_command' key classes without a one-word gloss.

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?

An output schema exists and the description still usefully names approval_url as part of the response, and annotations already cover the destructive/openWorld profile. The remaining gap is what an agent should do after receiving a PENDING result, presumably poll via send_status, which is never mentioned.

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 both parameters are already documented, including draft_id's origin from draft_letter. The description only implies that draft_id refers to a draft that will be mailed and adds no format or constraint detail beyond the schema, so the 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 action and target: submit a draft for mailing. It is clear about what is being requested, but it never distinguishes this tool from the send_status and send_fax siblings that appear in the same tool set, so an agent must still infer which one submits versus tracks a delivery.

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 two key tiers implicitly tell an agent what will happen depending on the key it holds, which is useful context. But it never says when to pick request_send rather than send_fax, nor how to follow up on a PENDING request; there is no explicit use-when/do-not-use guidance.

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.