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?
Annotations already provide destructiveHint=true and readOnlyHint=false, so the description's mention of 'delete' is consistent but adds little new behavioral context. It adds some context about data sensitivity but no additional behavioral details beyond the annotations.
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 concise: two sentences with no wasted words. The first sentence front-loads the action, and the second provides usage context. Every sentence is purposeful.
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 one-parameter delete tool with no output schema, the description covers purpose, usage conditions, and relationships to sibling tools. It is complete and sufficient for an AI agent.
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 description mentions 'by key', which aligns with the single required parameter 'key'. However, the schema already describes the key as 'Memory key to delete' (100% coverage), so the description adds no extra parameter meaning.
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') and the resource ('previously stored memory by key'). It distinguishes from sibling tools like '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?
The description provides explicit use cases: 'when context is stale, the task is done, or you want to clear sensitive data'. It also recommends pairing with 'remember and recall', giving clear guidance on when to use alternatives.
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 clusters have overlapping purposes: the three ask_pipeworx variants are nearly identical, polymarket_edges and polymarket_arbitrage both scan for opportunities, and ai_visibility_check vs scan_competitor_ai_presence create confusion. Although descriptions are detailed, an agent could easily misselect among these.
Most tools follow snake_case verb_noun (get_article, search_journals, resolve_entity), but there are brand-prefixed names (ask_pipeworx*, pipeworx_trending, pipeworx_feedback) and noun-phrase tools (entity_profile, bet_research) that break the pattern. The three ask_pipeworx variants are consistently named but confusable.
35 tools is excessive for a coherent server, especially one where many tools are meta-routes (ask_pipeworx, deep_research) that could consolidate functionality. The count exceeds the 25-tool threshold for 'heavy' and includes several one-off tools (generate_llms_txt, scan_dependency) that don't fit the dominant data-access theme.
The DOAJ subset is complete for read-only search and retrieval, but the server lacks a clear domain: it mixes DOAJ, prediction markets, memory, and subscriptions. For the broader Pipeworx platform, there are some dead ends (e.g., no subscription editing, no raw historical market data, no batch tools), and the non-DOAJ tools create confusion about what the server is actually for.