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 idempotentHint=true. Description adds usage context but no additional behavioral traits beyond what annotations convey.
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, front-loaded with action, no wasted words. Efficient and clear.
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 annotations present. Description covers purpose, usage, and pairing. No gaps for this complexity.
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% with a single parameter 'key' fully described. Description adds no extra parameter meaning beyond 'by key'.
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?
Description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes from sibling tools like 'remember' and 'recall' by mentioning pairing.
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 when to use: stale context, task done, clear sensitive data. Mentions pairing with remember and recall, but no explicit when-not scenarios.
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 groups have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, polymarket_edges / polymarket_arbitrage / polymarket_edge_tracker / polymarket_fill_risk / polymarket_kalshi_spread / bet_research all push prediction-market opportunities and can be confused, and ai_visibility_check is nested inside scan_competitor_ai_presence. discover_tools and suggest_questions also overlap as tool-discovery entry points.
Everything is snake_case and mostly descriptive, but conventions are mixed: verb-first names (resolve_entity, validate_claim, compare_entities, search_within) sit beside noun-first names (entity_profile, recent_changes, bet_research, polymarket_edges), and brand-prefixed tools (pipeworx_feedback, pipeworx_trending) have unprefixed functional siblings (list_subscriptions, recent_alerts). The two actual Base64 tools (base64_encode, base64_decode) don't match the dominant Pipeworx naming style at all.
33 tools is heavy for any single server, and the mismatch is extreme: the server is named 'Base64' yet only 2 of 33 tools relate to encoding/decoding — the other 31 form a sprawling data-research platform. Even judged as a data platform, the count exceeds the comfortable range and includes near-duplicates (the ask_pipeworx family, the Polymarket family).
The factual-data surface is well covered: query, grounded lookup, deep research, entity profiling, comparison, claim verification, entity resolution, subscriptions (subscribe/list/unsubscribe/recent_alerts), memory (remember/recall/forget), feedback, and tool discovery all exist with no obvious dead ends. The Base64 encoding domain is also complete (encode/decode across four variants). Minor gaps exist (e.g., no way to update a profile or edit memory entries) but they're workable.