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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (destructiveHint=true), the description explains the rationale for deletion and the context, adding value about when deletion is appropriate.
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 concise sentences, front-loaded with the primary action, followed by usage guidance and related tools. 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?
For a simple single-parameter tool with no output schema, the description provides complete information: purpose, when to use, related tools, and parameter usage.
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?
Only one parameter 'key' is described; the schema already provides a description ('Memory key to delete'). The description adds no further detail beyond suggesting it matches keys from 'remember' and 'recall', which is minimally helpful.
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 action ('Delete'), the resource ('previously stored memory'), and the method ('by key'). This distinguishes it from sibling tools 'remember' (create) 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 specifies when to use the tool ('context is stale, the task is done, or you want to clear sensitive data') and provides guidance to pair with related tools 'remember' and 'recall'.
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.
Most tools are distinct (event search, subscriptions, memory, Polymarket arbitrage, data lookups), but ai_visibility_check, scan_competitor_ai_presence, bet_research, polymarket_edges, and polymarket_arbitrage have overlapping purposes around competitive research and prediction-market edge-finding. The detailed descriptions disambiguate them, though an agent could confuse polymarket_edges with polymarket_arbitrage.
Tool names are mostly descriptive and consistent: search_events, event, categories, tags are aligned; ask_pipeworx, compare_entities, entity_profile follow a similar pattern. However, polymarket_* tools have an odd mix of `polymarket_arbitrage`, `polymarket_fill_risk`, and `polymarket_edge_tracker`, and discover_tools/recent_alerts/recent_changes are consistent, mostly. Naming is quite consistent overall with minor deviations.
At 35 tools, the count is heavier than typical MCP servers, but it reflects a broad service (Funcheap data + Pipeworx data platform + pred markets). Still, plenty of tools serve the same primary purpose (polymarket_, ask_pipeworx variants) so some pruning would improve the surface.
The surface appears complete for its domain: search/retrieve events, category/tag navigation, memory, subscriptions (create/list/cancel/pull), data lookups, entity resolution, comparisons, profiles, edge scanning, and feedback. Minor gaps include no direct 'update' on events (but events are static), and no pricing fetch tool separate from event text, though body text covers it.