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?
Description adds behavioral context (e.g., clearing sensitive data) beyond the annotations. Both destructive and idempotent hints are matched, no contradictions.
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?
Extremely concise: two sentences that front-load the action and purpose, with 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?
Complete for a simple tool: explains purpose, usage guidance, and pairing with siblings. No missing elements.
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% and the description does not significantly add beyond what the schema provides for the single 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 clearly states 'Delete a previously stored memory by key' with a specific verb and resource, and distinguishes from siblings by mentioning 'remember' and 'recall'.
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 ('context is stale, task is done, clear sensitive data') and pairs with alternatives, providing clear guidance.
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 (currently identical), ask_pipeworx_grounded, deep_research, and validate_claim all answer natural-language questions over the same underlying data sources. ai_visibility_check and scan_competitor_ai_presence also overlap as single vs. comparative variants. The detailed descriptions help, but the boundaries between the query/research tools remain genuinely ambiguous for an agent.
No consistent global naming convention. There are prefix families (amp_*, pipeworx_*, polymarket_*) but within them the structure varies (amp_get_events vs amp_user_search; ask_pipeworx vs polymarket_fill_risk), and many tools are bare verbs or noun phrases (remember, recall, forget, bet_research, search_within, recent_alerts). The mix of verb-first and noun-first names with irregular prefixes makes predicting tool names unreliable.
36 tools is too many for the server's nominal purpose: only 5 of them (amp_*) relate to Amplitude analytics, while the other 31 form a sprawling all-in-one data/research/prediction-market platform. Even accepting that broader scope, many tools could be consolidated (ask_pipeworx_beta duplicates ask_pipeworx, several polymarket tools are specialized but still numerous), making the count feel padded rather than focused.
The Pipeworx side is thorough: lookups, grounded verification, deep research, entity profiles, comparisons, subscriptions, and memory cover most of that domain well. However, the Amplitude analytics side is thin — it only queries events, active users, retention, and user activity, with no way to manage projects, cohorts, event definitions, or user properties. There is also no general web search tool and no direct database/SQL exploration, leaving notable gaps for the advertised all-in-one positioning.