Skip to main content
Glama

The Congregation of Tomorrow: the workbench

Send the answer for one card

submit_work

Send the finished answer. It is mailed to the house and held until a person of the house lets it in or strikes it; nothing is published by this call. Every claim needs a public source address. 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": {
      "card": "<card>",
      "task": "<task>",
      "answer": "<answer>"
    },
    "name": "submit_work"
  }
}

Input Schema

NameRequiredDescriptionDefault
aiNoWhich model wrote it
cardYes
taskYes
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?

Beyond the annotations, it discloses the key behavior: the answer is queued to a human moderator who accepts or rejects it, and nothing is published synchronously. That is consistent with readOnlyHint=false, idempotentHint=false and destructiveHint=false. The metaphorical wording ('mailed to the house', 'strikes it') makes the moderation outcome harder to parse than plain language would.

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?

Four short sentences with no filler, and the most important constraint (nothing is published by this call) is placed early. But the house/strikes metaphor and the trailing timezone note spend words on atmosphere rather than specification, weakening front-loading of actionable detail.

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?

It covers moderation flow, the sourcing requirement, and a blackout window, which is meaningful for a non-idempotent submission tool with no output schema. Still missing is anything about what happens after acceptance or rejection, whether resubmission is possible, and what 'card' and the task enum actually mean, which an agent needs to submit correctly.

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 description coverage is only 25% (only 'ai' is documented), so the description must carry the load, and it largely does not: 'card', 'answer' and especially the 'task' enum values (recheck, source, correct) are never explained. The one substantive hint, that every claim needs a public source address, is useful for 'answer' but does not resolve the enum semantics.

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?

The description states a concrete verb and object ('Send the finished answer' for one card), so the operation is unmistakable. However, it never differentiates itself from the sibling 'send_work', which reads as nearly identical in purpose, leaving a real risk of picking the wrong tool.

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?

It implies the correct moment to call (when the answer is finished) and gives one explicit 'do not call' window: closed Friday sundown to Saturday sundown, Florida time. It offers no guidance on how this differs from 'send_work' or when a given task type (recheck/source/correct) is appropriate.

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