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 declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds rationale (clearing sensitive data) and pairing guidance, but does not elaborate on failure behavior or permanence beyond what annotations imply.
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?
Three concise sentences, front-loaded with the primary action, followed by usage context and a pairing hint. Every sentence earns its place with no redundancy.
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 tool with no output schema and strong annotations, the description covers purpose, when-to-use, and relationship to peers. Nothing significant is missing.
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 description coverage is 100% – the single parameter 'key' is described as 'Memory key to delete'. The description echoes this ('by key') but does not add additional semantics or constraints beyond the 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?
The description clearly states 'Delete a previously stored memory by key' with a specific verb and resource, and the by-key scope distinguishes it from siblings like remember (store) 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?
Provides explicit when-to-use conditions: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also directs pairing with remember and recall, clarifying the tool's role within the memory tool family.
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.
Many tools overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, entity_profile, compare_entities, and validate_claim all serve data-lookup purposes with unclear boundaries. The three xkcd comic tools are distinct but are buried under 31 unrelated tools, making selection confusing.
Tool names follow no consistent pattern: some use verb_first (get_comic, list_subscriptions), some are nouns (entity_profile, deep_research), some have prefixes (ask_pipeworx_*, polymarket_*), and others are vague (scan_dependency, generate_llms_txt). The mixing of styles across the set makes it hard to predict naming.
With 34 tools and a server name of 'xkcd', the count is wildly disproportionate; only 3 tools relate to comics. Even as a general data-access server, 34 tools is heavy and many are meta-tools (discover_tools, suggest_questions) that add bulk.
For the actual Pipeworx data domain, the surface is fairly comprehensive: querying, grounded answers, research, entity profiles, comparisons, validation, subscriptions, and prediction-market analysis are covered. However, there are notable gaps like no fetch-by-URI tool and no xkcd search/list capability, making the set incomplete for its name and slightly incomplete for its inferred domain.