Slack MCP server has well-structured tool definitions with consistent naming (verb_noun pattern) and complete input schemas. All 8 tools have descriptions and typed parameters. However, descriptions are generic and lack LLM-optimized guidance on WHEN to use each tool vs. alternatives. Output schemas are not documented, LLMs cannot predict response structure for chaining. Error handling is absent from visible code. Parameter descriptions lack format constraints, ranges, and dependency hints. No tool annotations (readOnlyHint/destructiveHint) despite clear risk stratification (READ_ONLY vs WRITE). Missing pagination guidance and result limits in descriptions.
Add a reaction emoji to a message
Get recent messages from a channel
Get all replies in a message thread
Get detailed profile information for a specific user
Get a list of all users in the workspace with their basic profile information
List public channels in the workspace with pagination
No output schemas documented. LLMs cannot predict response structure, breaking tool chaining. E.g., slack_list_channels returns channels but response fields are unknown to the agent.
Descriptions lack LLM-optimized guidance. Generic descriptions (e.g., 'Post a new message to a Slack channel') do not explain WHEN to use this tool vs. slack_reply_to_thread, or what happens on success/failure. Baseline: 194 chars avg; these are ~50 chars.
No tool annotations (readOnlyHint/destructiveHint/idempotentHint). Tools are marked READ_ONLY or WRITE in metadata but not in schema. LLMs cannot infer safety/retry semantics without explicit hints.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 53 | 2026-07-28+ | v2 |
Post a new message to a Slack channel
Reply to a specific message thread in Slack
Parameter descriptions lack format constraints and ranges. E.g., 'limit' has no min/max bounds (default 100, max 200 stated but not enforced in schema). 'thread_ts' format is explained in prose but not as a regex pattern or format constraint.
No error handling guidance visible in code. Tool descriptions do not explain what errors can occur, how to recover, or what the LLM should do next (e.g., 'Channel not found, try slack_list_channels to find valid channel IDs').