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; the description adds context about clearing sensitive data and assumes idempotent behavior, consistent with 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 concise sentences: first states the action and resource, second provides usage guidance and pairing suggestions. No waste.
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 tool with one parameter and no output schema, the description fully covers purpose, usage, and pairing recommendations.
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 'key' parameter described as 'Memory key to delete'. The description adds no additional semantic value 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 the action ('Delete a previously stored memory by key') and resource ('key'), and the tool is distinct 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?
Explicitly provides when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing with 'remember' and 'recall', giving clear context and 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.
The ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) has significant boundary overlap, and ask_pipeworx_beta is explicitly identical to ask_pipeworx today. The six polymarket_* tools plus bet_research also cover heavily overlapping prediction-market territory, so an agent could easily route a query to the wrong one despite detailed descriptions.
Most tools follow a consistent snake_case verb_noun pattern (ask_pipeworx, compare_entities, generate_llms_txt, list_subscriptions, validate_claim, scan_dependency). Minor deviations exist — entity_profile is noun-noun, brightdata_serp/brightdata_unlock use a vendor prefix, and remember/recall/forget are bare verbs — but the overall style is predictable and readable.
At 33 tools this exceeds the 25+ threshold that signals an over-heavy surface. While the server covers multiple domains (data lookup, prediction markets, memory, subscriptions, AI visibility), many of those domains carry redundant variants that could be consolidated, making the count feel bloated rather than well-scoped.
The surface covers the core workflows well: querying (ask_pipeworx variants), deep research, entity resolution, entity profiles, comparisons, change feeds, claim verification, discovery/onboarding, subscriptions (list/subscribe/unsubscribe), memory (remember/recall/forget), and feedback. Minor gaps exist — there is no direct tool to fetch a returned pipeworx:// citation URI, and memory lacks an explicit update operation — but agents can work around these.