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. Description confirms deletion by key but adds no extra behavioral detail. No contradiction.
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 sentences: first states purpose, second provides usage guidelines. No wasted words.
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?
Simple tool with one parameter and no output schema. Annotations cover safety. Description adds pairing guidance, fully sufficient.
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 has 100% coverage with description 'Memory key to delete'. Description repeats 'by key' without adding new meaning. Baseline 3 acceptable.
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?
Clearly states 'Delete a previously stored memory by key' – specific verb and resource. Distinguishes from siblings 'remember' (store) and 'recall' (retrieve).
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 lists three scenarios (stale context, task done, clear sensitive data) and names complementary tools. Lacks explicit when-not-to-use, but guidance 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.
Several tools are nearly indistinguishable without deep reading: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded all route the same universal query, and the beta currently behaves identically. The prediction-market clister (polymarket_arbitrage, pollymarket_edges, pollymarket_edge_tracker, pollymarket_fill_risk, pollymarket_kalshi_spread) and value-estimation tools (attom_avm, attom_assessment, attom_rental_avm) have fuzzy boundaries that will cause misselection.
The vast majority of tools follow a consistent lower_snake-case convention with clear prefixes (attom_*, polymarket_*, pipeworx_*) and verb-noun forms (generate_llms_txt, list_subscriptions, resolve_entity). Minor deviations exist like the bare memory verbs remember, recall, forget and domain-noun names entity_profile, bet_research, but the overall pattern is predictable and readable.
39 tools is well above the comfortable 3-15 range and signals scope creep: the server bundles real-estate, prediction markets, company research, memory, subscriptions, web utilities, and a universal data router. Many of these could be grouped into a smaller number of composite tools, as the descriptions themselves already suggest (e.g. ask_pipeworx as the default entry point).
Coverage is deep for prediction markets, company financials, and real-estate, with complete memory and subscription lifecycles (remember/recall/forgeet, subscribe/list/unsubscribe/recent_alerts). However, many advertised domains (weather, clinical trials, news, government records) are only reachable through the generic ask_pipeworx router rather than dedicated tools, and scan_dependency is npm-only, leaving obvious gaps for other ecosystems.