Skip to main content
Glama

goodbotbad.bot

by bot.goodbotbad

Submit a transcript for the crowd to rule on

submit_transcript

Submit an AI prompt and the response it produced to goodbotbad.bot, where people vote good bot or bad bot on it. NOTHING IS PUBLISHED BY THIS CALL. It creates a draft and returns a URL; a human has to open that URL and confirm before anything becomes visible, and you should show them the URL. There is deliberately no note parameter — the note is the human's account of why the exchange is worth posting, they write it on that page, and it is not something to compose for them. Secrets and API keys are detected and the submission is refused outright. Personal data — an email address, a phone number, a home directory path — is redacted before storing and named in the reply; show your human what was removed along with the URL. Quote the prompt verbatim if you can; if the real input was too large or is not recoverable, describe it in objective instead and say so. If the transcript is larger than 65536 bytes, send manifest INSTEAD of turns — a role, a byte count and a short label per turn, and no bodies — and the server will ask your human which passages to send. Do not send the bodies and let the server reject them: that has already disclosed them. To submit a repair for a failure already on the site, pass its id as fixes — a fix is a rewritten prompt and the better response it produced, so its verdict is good, and it waits on two people rather than one: a moderator screens it, and whoever posted the failure decides whether it repairs it. If the reply asks for token usage, it is asking your human and not you — they read it off their own client, which you cannot see. Put what they say in inputResponses.usage and send the whole call again with the requestState; it attaches to the draft that already exists rather than making a second one. Never supply a figure of your own, and skipping is a fine answer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixesNoThe id of a published post the crowd ruled bad bot, if this transcript is the repair of it. The id search_posts and get_post return.
modelYesThe model or product that produced it, as its own name.
titleYes
turnsNoThe exchange in order. Omit when sending a manifest. Use role `attachment` for an image or file that was part of the exchange — its body describes what was there, since only text is stored.
usageNoToken counts, if your client has genuine API metadata. Omitted is better than guessed.
verdictYesYour human's ruling, not yours.
categoryYes
manifestNoDescribes an oversized transcript without sending it: role, bytes and a short label per turn.
source_urlNo
requestStateNoEcho back untouched from a previous inputRequired reply.
inputResponsesNoAnswers to a previous inputRequired reply.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixesNoThe id of the failure this repairs, if it is a repair.
stateNo`draft` on submission. Later legs report where the post has since got to.
draft_urlNoWhere your human confirms it. Nothing is published until they do.
public_idNo
redactionsNoWhat was redacted before storing, named so your human knows what changed. Empty when nothing was.
usage_sourceNo`attested` when a human typed the figures. Null when they declined.

TDQS

A4.5/5.0
Behavior4/5

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

Annotations indicate readOnlyHint=false (writes), openWorldHint=true (external interaction), destructiveHint=false. The description correctly and thoroughly explains behavioral traits: nothing is published immediately, secrets auto-rejected, personal data redacted, oversized transcripts handled via manifest. One minor gap: it doesn't explicitly state that the server enforces size limits, but the manifest workaround is described. No contradiction with annotations.

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?

The description is dense and comprehensive but notably long. Every sentence earns its place for a complex multi-step tool, yet it could benefit from clearer sectioning or bullet-like formatting for quicker parsing by an AI agent. The front-loading is acceptable (core submission action first), but the wall of text reduces scanability.

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?

Given the tool's high complexity (11 parameters, nested objects, multiple workflows) and presence of an output schema, the description covers almost all critical behavioral paths: draft creation, confirmation URL, secret detection, manifest flow, repair submission, token handling. Slight lack on what the output schema contains (the reply structure) but output schema itself provides that.

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

Parameters5/5

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

Schema coverage is 73%, but the description vastly enriches understanding of parameters like manifest vs turns, fixes lifecycle, usage (human-provided, not AI-generated), and inputResponses. It explains roles not obvious from schema (e.g., attachment for non-text content) and nuances like quoting verbatim vs using objective.

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?

The description clearly states the tool is for submitting an AI prompt-response pair to goodbotbad.bot for crowd voting. It distinguishes itself from siblings like search_posts/get_post by explaining the submission lifecycle (draft creation, human confirmation step).

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?

The description provides extensive when-to-use guidance, including when to send manifest instead of turns for oversized transcripts, how to handle repairs via fixes, and how to respond to inputRequired replies. It also clarifies when NOT to send bodies (to avoid disclosure) and distinguishes this tool from the human's own token logging.

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

All goodbotbad.bot toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

The tools are mostly distinct: search_posts and get_post are clearly read-only, submit_transcript is the main submission path, and complete_pair handles the paired-transcript workflow. The only mild overlap is between complete_pair and submit_transcript since both stage unpublished content, but their trigger conditions are explicit enough to avoid serious misselection.

Naming Consistency5/5

Every tool follows a clear verb_noun snake_case pattern: complete_pair, get_post, search_posts, submit_transcript. The naming is predictable and consistent, with no mixing of conventions or vague verbs.

Tool Count5/5

Four tools is well-scoped for this narrow domain: search and fetch for reading, submit for the primary write path, and complete_pair for the site's pairing mechanic. Each tool has a real purpose and the count does not feel bloated or thin.

Completeness4/5

Core workflows are covered: searching existing posts, fetching details, submitting transcripts, and completing pairs. The main gap is that once a draft or pair candidate is staged, there is no way for the agent to check its status or whether it has been approved, though this may be intentional since humans handle confirmation.

Resources