Loading ToolBench

Reading the current corpus…

discord-ops MCP server · F · ToolBench

← Browse

discord-ops

github.com/bookedsolidtech/discord-ops

Agency-grade Discord MCP server with multi-guild project routing

<=2025-11-25STDIO72 tools

41/100

Definition Quality38

Protocol Readiness42

Supportability45

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

discord-ops exposes 72 tools with minimal schema documentation and sparse parameter descriptions. While tool names follow verb_noun conventions (send_message, get_channel, delete_role), most tools lack visible input schemas in the provided source. The server.ts excerpt shows Zod schema parsing but does not reveal individual tool schema definitions. Parameter descriptions are absent or trivial across the tool list. Output schemas are undocumented. Error handling is generic (rate limit responses only). Security audit logging exists but permission gates are not visible per-tool. The codebase is well-structured (profiles, rate limiting, sanitization) but tool definitions themselves are under-specified for LLM reasoning.

Tools (72)

add_reactionwriteauthsource verified38/100

Add a reaction to a Discord message

archive_threadwriteauth38/100

Archive a Discord thread

assign_rolewriteauth38/100

Assign a role to a Discord guild member

ban_memberdestructiveauthsource verified38/100

Ban a member from a Discord guild

create_app_emojiwriteauth38/100

Create an application emoji

create_channelwriteauthsource verified38/100

Create a new Discord channel

create_forum_postwriteauth38/100

Create a post in a Discord forum channel

create_invitewriteauth38/100

Issues (5)

CRITICALconstrained-input ↗

No input schemas visible in source code. All 72 tools lack documented parameter types, constraints, and validation rules. The server.ts shows Zod parsing but individual tool schema definitions are not provided.

send_messageget_messagesedit_messagedelete_messagecreate_channelban_memberdelete_webhook

CRITICALtool-description ↗

Tool descriptions are trivial (10-30 chars). LLMs cannot determine when to select a tool or what it does. E.g., 'Send a message to a Discord channel' lacks context on required parameters, return value, or when to use vs. send_embed or send_template.

send_messagesend_embedsend_templateedit_messagedelete_messageban_memberkick_member

CRITICALtool-description ↗

No parameter descriptions visible. LLMs cannot infer what 'project', 'channel', 'user_id', or 'role' parameters mean, their valid ranges, or whether they accept names vs. IDs. This forces agents to guess or make extra discovery calls.

Recommendations

Document input schemas for all 72 tools. For each parameter, specify type (string, number, enum), constraints (min/max, regex, allowed values), and whether it is required. Use Zod's built-in descriptions or JSON Schema 'description' fields.
Expand tool descriptions to 50 - 200 characters. Include WHAT the tool does, WHEN to use it (vs. similar tools), and what it returns. E.g., 'Send a message to a Discord channel. Use send_embed for rich formatting or send_template for predefined layouts. Returns message_id and timestamp.'
Add descriptions to every parameter. Clarify whether parameters accept IDs, names, or both. E.g., 'channel: Channel ID or name (string). If a name, the bot searches the guild for a matching channel.'
Document output schemas and pagination. For list_* tools, specify returned fields, total_count, next_cursor, and max result limits. E.g., 'Returns array of {id, name, created_at, member_count} with max 50 items per page.'
Add confirmation or dry-run patterns to destructive tools. E.g., delete_message should accept a 'confirm' boolean parameter, or offer a separate 'preview_delete' tool that shows what would be deleted without executing.

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

41/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	41	<=2025-11-25	v2