forgetDelete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Memory key to delete |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide destructiveHint and idempotentHint. Description adds 'delete' and 'clear' which match annotations but no additional behavioral context beyond schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences that cover purpose and usage without waste; front-loaded with core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a simple delete tool with one parameter; annotations cover destruction; could mention irreversibility but not critical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter, and the description does not add meaning beyond what the schema already provides for the 'key' parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Delete a previously stored memory by key', specifying the verb, resource, and method, and distinguishes from siblings by mentioning 'remember' and 'recall'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit when-to-use scenarios (context stale, task done, clear sensitive data) and pairs with sibling tools, but lacks explicit when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The five Slack tools are distinct, but the rest of the set is a sprawling bundle of Pipeworx, prediction-market, memory, and subscription tools with several overlapping pairs: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded share the same router, while discover_tools and suggest_questions both act as discovery entry points and scan_competitor_ai_presence wraps ai_visibility_check. An agent would frequently have to read long caveats to choose the right tool.
Most names are descriptive snake_case and the Slack tools share a clean slack_ prefix, but the broader set mixes verb-led names (ask_pipeworx, generate_llms_txt, validate_claim) with noun-style names (entity_profile, pipeworx_trending, ai_visibility_check) and a few bare verbs (remember, recall, forget, subscribe). It is readable but does not follow a single predictable pattern.
36 tools is above the 25+ threshold and far more than a Slack connector needs: only five tools actually interact with Slack, while the other 31 are unrelated Pipeworx research, prediction-market, memory, and subscription features. The set reads as a kitchen-sink bundle rather than a focused integration.
For a Slack_connect server, the surface is only partially complete: it can list channels/users, join, read history, and send messages, but common Slack operations like threads, reactions, message update/delete, channel creation/archiving, and direct messages are missing. The unrelated data tools do not fill these gaps, so the actual Slack domain would still cause agent failures.