Skip to main content
Glama
Sign In

Samuelz® Marketing

by com.samuelz.platform
OverviewDiscussionsAdmin

Briefwelle freigeben

confirm_letter_wave_send
Destructive

App only. After the human clicks Confirm, approve the exact quoted letter wave for background dispatch. The result confirms approval only. For submission or delivery status, read get_letter_wave. Models use request_letter_wave_send to show the card and must never call this tool. The app copies the candidate and approval token from that card unchanged. If approval is expired, stale, or uncertain, read get_letter_wave. Request a fresh card only if the wave is still ready for approval.

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": {
      "candidate": "<candidate>",
      "approvalToken": "<approvalToken>"
    },
    "name": "confirm_letter_wave_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
candidateYesExact candidate from the same card's hidden metadata. Copy every field unchanged.
approvalTokenYesOpaque proof from the same card's hidden metadata, bound to the candidate, tenant, user, and OAuth grant. Copy it unchanged.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare a destructive, non-idempotent mutation but say nothing about caller identity or failure modes; the description fills that gap by stating the tool is app-only, that the result confirms approval only (not submission or delivery), that approval can expire and become stale, and that the candidate and token are bound and copied unchanged. This is substantial behavioral context beyond the annotation surface, and it is consistent with destructiveHint=true.

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?

Front-loaded with the hard constraint ('App only') and ordered as purpose, result semantics, alternatives, token provenance, recovery. Slightly dense at six sentences with get_letter_wave named twice, but each sentence carries a distinct operational rule and none is filler.

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, nested-parameter mutation with no output schema, the description covers who may call it, when, what the return means, and how to recover from stale approvals. Nothing an agent needs before invoking or declining to invoke this tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the description earns a bump by stating that the app copies the candidate and approval token from the card unchanged, which tells the agent these values are opaque and must not be synthesized or edited. It does not add format or field-level detail beyond the schema, so it stops short of 5.

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?

States a specific verb and resource ('approve the exact quoted letter wave') plus the mechanism ('background dispatch'), and explicitly distinguishes itself from get_letter_wave (status) and request_letter_wave_send (card creation). An agent can identify this tool's role without opening the 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?

Gives an explicit prohibition ('Models ... must never call this tool'), names the alternative (request_letter_wave_send) and the exact trigger ('After the human clicks Confirm'), and adds recovery routing: expired/stale/uncertain approvals go to get_letter_wave, and a fresh card is only requested if the wave is still ready. Both when-to-use and when-not-to-use are covered.

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

All Samuelz® Marketing toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources