Skip to main content
Glama
wudpecker

Worth Sending

Official
by wudpecker

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_message_rubricA

Get the evidence requirements, rating anchors, weights, and mandatory decision rules before evaluating a discretionary product-adoption message.

evaluate_messageA

Enforce the message value rubric on your evidence-backed assessment. Read get_message_rubric first. Provide the exact message, context, evidence, and your per-dimension judgments. Returns send/revise/hold, score, reasons, and required changes. Missing context returns hold. The server checks references and rules; the calling agent judges meaning and truth. It never dispatches a message.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
message-value-rubricAgent instructions and provisional decision policy for adoption messages.

TDQS

A4.2/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one retrieves the rubric, the other performs the evaluation. The descriptions explicitly state that the rubric should be read first, eliminating any confusion about which tool to use when.

Naming Consistency5/5

Both tool names follow a consistent snake_case verb_noun pattern: get_message_rubric and evaluate_message. The slight variation in noun phrase length does not break the predictable convention.

Tool Count4/5

With only 2 tools, the set is slightly below the typical 3-15 range, but each tool is essential for the server's narrow purpose. The minimal count is justified by the focused workflow of fetching a rubric and then evaluating a message.

Completeness5/5

The two tools cover the full lifecycle for evaluating a message: obtaining the rubric and performing the assessment. No obvious operations are missing for the stated domain, and the server explicitly does not dispatch messages, so no send tool is needed.

Maintenance

ActivityMaintained
ResponsivenessNo issues