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?
The description adds some context beyond annotations by clarifying the tool deletes memories and is used for clearing sensitive data. However, it does not disclose details like error behavior for missing keys or confirmations, and it does not mention idempotency despite the idempotentHint. The annotations already cover destructiveHint, so the description provides only marginal additional transparency.
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 long, with each sentence serving a purpose: first defines the action, second gives usage context. No unnecessary words. Front-loads the core purpose effectively.
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 delete tool with one required parameter and no output schema, the description covers purpose, usage context, and pairing with siblings. It lacks details on error handling or behavior when key doesn't exist, but overall it is sufficiently complete for the tool's simplicity.
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%, so baseline is 3. The parameter 'key' has a clear description in the schema ('Memory key to delete'). The description says 'delete by key', which is already implied by the schema. No additional meaning is added.
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 the verb 'delete' and the resource 'memory by key'. It distinguishes this tool from siblings by explicitly mentioning 'remember' and 'recall' as tools to pair with, making its role clear.
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?
The description provides explicit when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. It also suggests pairing with related tools. It lacks explicit when-not-to-use guidance, but the positive advice is strong.
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.
Multiple near-duplicate clusters exist: ask_pipeworx, ask_pipeworx_beta (explicitly identical to the stable router right now), and ask_pipeworx_grounded all route through the same 5,767-tool catalog, and six polymarket_* tools overlap heavily in surfacing bet/edge opportunities. The blocklist tools (list, recent, aggressive) are only weakly distinguished by time window and confidence, requiring careful reading to select correctly.
Naming mixes several incompatible conventions: bare adjectives/nouns for blocklist tools (aggressive, list, recent), brand-prefixed compounds (polymarket_arbitrage, pipeworx_feedback), verb_noun pairs (check_ip, resolve_entity), and noun phrases (entity_profile, bet_research). The server name 'Feodotracker' appears nowhere in the tool names, and the blocklist cluster uses a completely different style from the data cluster.
At 35 tools, the count exceeds the 25-tool threshold for 'too many', but the deeper issue is that roughly 31 tools serve a general data-lookup/prediction-market platform while only 4 serve the server's stated Feodotracker blocklist purpose. The count reflects two unrelated products merged into one MCP server rather than a well-scoped tool surface.
For the named Feodotracker domain, the surface is thin: list/check/recent cover basic blocklist access but miss historical lookups, per-entry threat intel, or export formats that a botnet tracker would need. For the data-lookup domain the 31-tool suite is impressively complete, but the two domains don't form a coherent whole—each leaves the other's lifecycle half-served.