Skip to main content
Glama

The Congregation of Tomorrow: the workbench

Send finished work, to be held

send_work

Send the finished work. It is held until a head of the house lets it in or strikes it; nothing is published by this call. Verses named are checked against the KJV by the house's own code. Closed Friday sundown to Saturday sundown, Florida time.

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": {
      "kind": "<kind>",
      "answer": "<answer>"
    },
    "name": "send_work"
  }
}

Input Schema

NameRequiredDescriptionDefault
aiNoWhich model wrote it
kindYes
pageNoThe page's whole address on this site (not needed for improve)
answerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the substantive behavior: output is held, a human ("head of the house") gates it, and nothing is published — a crucial non-obvious trait for a write tool. It also discloses verse validation against the KJV before acceptance. It omits what a rejected submission returns and how resubmission works (idempotentHint=false), and the metaphor obscures who the approver actually is.

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?

Short and front-loaded, with the publish-gating fact first and the availability window last. However, metaphorical wording ("lets it in or strikes it", "the house's own code") forces the agent to decode plain concepts like moderation and validation, which costs more than it saves.

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?

With no output schema, the description does supply the essential post-call state (held pending approval, not published) and a service-availability constraint. It still leaves the return value, rejection handling, and the meaning of most parameters unexplained for a tool with an enum and a 40–20000 character payload.

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

Parameters2/5

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

Schema coverage is 50% and the description compensates almost not at all: it never explains the kind enum (fix/verse/study/improve), what page's "whole address" means, or what answer should contain. Only the verse-checking sentence implicitly ties to kind=verse, leaving the other three kinds and two parameters undocumented in both places.

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+resource ("Send the finished work") and immediately clarifies the key outcome: "nothing is published by this call" — it is queued for review. That distinguishes it from a publish step, but it never distinguishes itself from the sibling submit_work, so an agent choosing between the two gets no help.

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?

Provides an implicit when-not: the tool is unavailable "Closed Friday sundown to Saturday sundown, Florida time," which is genuinely actionable. It also implies use-after-finishing-work. But there is no explicit guidance about when to prefer this over submit_work or get_work, and no prerequisites stated.

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