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 annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, covering the key safety behaviors. The description adds little beyond restating the deletion action; it mentions 'previously stored' and 'clear sensitive data' but these are preconditions and use-case rationales rather than new behavioral traits.
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-loads the action, and every clause serves a purpose. It is efficient without unnecessary detail.
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 single-parameter tool with rich annotations and no output schema, the description fully covers action, usage conditions, and tool relationships. It is contextually complete for an agent to select and invoke it correctly.
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 fully describes the 'key' parameter with 'Memory key to delete' and includes an example. The description adds no new parameter semantics, and with 100% schema coverage, this is sufficient.
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' with scope 'by key'. It distinguishes from siblings by referencing remember and recall, making its role in the memory trio explicit.
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 explicitly provides usage conditions: 'Use when context is stale, the task is done, or you want to clear sensitive data'. It also mentions pairing with remember and recall, indicating 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.
Several tool families have genuine boundary ambiguity: ask_pipeworx and ask_pipeworx_beta are currently identical in behavior, and the five Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) all live in the 'find/pursue an edge' space, requiring an agent to parse very long descriptions to choose correctly. The IP, memory, and subscription tools are clearly distinct, but the overlap-prone families cause real misselection risk.
All names are snake_case and each family is internally consistent (polymarket_*, ask_pipeworx_*, subscribe/unsubscribe, remember/recall/forget). However, conventions mix across the set: verb_noun (geolocate_ip, resolve_entity, validate_claim) coexists with noun-first names (entity_profile, pipeworx_feedback, recent_alerts) and bare verbs (remember, forget), so there is no predictable global pattern.
At 33 tools the set exceeds the heavy threshold, and the server name 'iplookup' covers only 2 of them; the remaining 31 form a sprawling data-research, prediction-market, memory, and subscription platform with tangential utilities like generate_llms_txt and scan_dependency. The broad scope means few tools are individually useless, but the server reads as a kitchen sink rather than a focused toolkit.
As an IP-lookup service the surface is thin: only geolocation and ISP data, with no WHOIS, reverse DNS, proxy/VPN detection, or reputation records. As a data-research platform the surface is strong (universal query routing, grounded verification, entity profiles, comparisons, subscription lifecycle, memory). This lopsidedness makes the actual domain ambiguous and leaves the namesake use case under-covered.