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.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true. Description adds 'delete by key' but no additional behavioral traits beyond 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?
Two sentences: first defines action, second provides usage guidance. No wasted words, front-loaded.
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?
Tool is simple (1 param, no output schema). Annotations cover safety, schema covers parameter. Description is sufficient for correct invocation.
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 parameter 'key' described as 'Memory key to delete'. Description does not add extra meaning beyond schema.
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 verb 'Delete', resource 'previously stored memory', and method 'by key'. It distinguishes from siblings '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: stale context, task done, clearing sensitive data. Mentions pairing with remember and recall. Lacks explicit when-not-to-use but provides 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 clusters have overlapping purposes: ask_pipeworx and ask_pipeworx_beta are explicitly identical, and the five prediction-market tools (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_kalshi_spread, polymarket_fill_risk) all target 'find edge in Polymarket markets' with subtle differences. query and variant both retrieve the same variant annotations, and ai_visibility_check vs scan_competitor_ai_presence are near-duplicates.
Most tools follow a consistent verb_noun or domain-prefixed pattern (ask_pipeworx, compare_entities, resolve_entity, polymarket_edges, remember/recall/forget). Minor deviations exist: the bare nouns query, variant, and metadata are less descriptive, and ask_pipeworx_beta uses a suffix instead of a clean verb pattern, but the overall convention is fairly uniform.
34 tools is far too many for a server named 'Myvariant' whose stated domain is genetic variant annotations. The set is a grab-bag spanning genetic data, Pipeworx query routing, Polymarket betting, memory persistence, subscriptions, AI visibility, and npm dependency scanning. Most tools are unrelated to the server's apparent purpose, making the count feel bloated and incoherent.
Individual clusters are reasonably complete: variants have search/get/metadata, memory has remember/recall/forget, and subscriptions have subscribe/list/unsubscribe/alerts. However, as a Myvariant server the surface is massively over-scoped yet oddly missing any batch-variant or annotation-source-specific lookup, and the sprawling multi-domain design makes 'complete' hard to meaningfully assess.