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. The description adds usage context but no new behavioral details (e.g., permanent deletion, behavior on missing key). It does not contradict annotations, but adds minimal transparency value beyond 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?
Three short, front-loaded, and purposeful sentences. The first sentence states the action, the second gives usage context, and the third notes related tools. No redundancy or filler.
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?
For a simple one-parameter tool with strong annotations (destructive, idempotent), the description covers the core purpose and usage scenarios. It is complete enough for an agent to select and invoke the tool correctly, including pairing with related memory tools.
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 description coverage is 100%, with the schema already documenting 'Memory key to delete'. The description restates 'by key' but does not add format, constraints, or edge-case semantics 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 uses a specific verb ('Delete'), names the resource ('previously stored memory'), and specifies the key mechanism. It clearly distinguishes itself from sibling tools like remember and recall, which store and retrieve memories 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?
Explicitly states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also mentions pairing with remember and recall, providing a clear coordination pattern.
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.
Several tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions, while the polymarket_edges, polymarket_arbitrage, and related tools blur edge-detection boundaries. The server's Bitstamp identity also clashes with the bulk of tools being unrelated data-research, making selection harder.
Tool names are all lowercase snake_case, which is consistent formatting, but no coherent verb_noun pattern emerges. Some are verb-first (ask_pipeworx, compare_entities, discover_tools) while others are noun-first or resource-based (ticker_hour, order_book, polymarket_edges), and the naming style differs across the two major domains.
At 38 tools, the set is well over the 15-tool threshold for a focused server, and the majority of tools are unrelated to the server's Bitstamp name. The count feels bloated and scattershot—it would be better split into separate data-research and exchange servers.
The data-research and question-answering surface is broadly covered, with meta-tools and validation. However, the Bitstamp exchange half is incomplete: it only provides public market data (ticker, order book, trades, OHLC) with no trading, account, or private-data operations, an obvious gap given the server's name.