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 declare destructiveHint=true and idempotentHint=true, so the deletion behavior is covered. The description adds context about clearing sensitive data and addressing stale context, which goes beyond annotations without contradicting them.
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?
The description is two sentences, front-loaded with the core action, and every word earns its place. It elegantly communicates purpose, usage, and related tools without any redundancy.
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?
Given the tool's simplicity (one required parameter, no output schema), the description fully covers its purpose, usage, and relationships to sibling tools. Annotations handle safety aspects, so the description is complete for effective tool selection and invocation.
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?
The schema covers the only parameter 'key' with the description 'Memory key to delete' at 100% coverage. The tool description does not add additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.
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 opens with a specific verb and resource: 'Delete a previously stored memory by key.' This clearly differentiates it from sibling tools 'remember' and 'recall' by indicating deletion, storage, and retrieval respectively.
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?
Explicit usage guidance is provided: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' This gives clear conditions for use, and 'Pair with remember and recall' suggests related tools.
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 ask_pipeworx family is a major confusion source: ask_pipeworx_beta explicitly states it 'currently matches ask_pipeworx exactly', and ask_pipeworx_grounded/deep_research heavily overlap with the base router. polymarket_edges vs polymarket_arbitrage and discover_tools vs suggest_questions also have fuzzy boundaries, though long descriptions partially mitigate the overlap.
All tool names are lowercase snake_case, and most follow a verb_noun pattern (validate_claim, resolve_entity, compare_entities, generate_llms_txt). A few bare verbs (remember, recall, forget) and noun-style names (entity_profile, polymarket_arbitrage, pipeworx_trending) deviate slightly, but the overall style is predictable and readable.
34 tools is heavy and spans several unrelated domains: Pipeworx data research, prediction markets, subscriptions, memory, AI visibility, advice slips, npm dependency checks, and llms.txt generation. The count is inflated by near-duplicate research routers and disconnected outliers like generate_llms_txt and scan_dependency, making the set feel like a kitchen sink rather than a focused server.
The Pipeworx research and prediction-market surfaces are quite complete (ask, grounded, deep research, entity profile, compare, resolve, validate, subscriptions with full lifecycle, memory with save/recall/delete). However, the server is named 'advice' yet the advice domain only has three thin tools (get/search/random) with no other operations, and the mixed domains leave obvious dead ends for any single stated purpose.