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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds the mechanism ('by key') but doesn't disclose failure modes or permanence beyond what annotations imply. Some added context, but limited.
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 short sentences front-load the purpose, provide usage guidance, and mention sibling pairing. No filler or 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 strong annotations and no output schema, the description covers purpose, usage conditions, and relationships to siblings. No critical information 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 covers the single 'key' parameter with a clear description ('Memory key to delete'), and the description's 'by key' adds no further semantic detail. High schema coverage justifies baseline 3.
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 states a specific verb ('Delete'), resource ('previously stored memory'), and method ('by key'), clearly distinguishing it 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?
Provides explicit use cases ('context is stale, task is done, or clear sensitive data') and mentions pairing with remember/recall. Lacks explicit 'when not to use' or named alternatives, but gives clear contextual 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.
Multiple tools serve overlapping purposes, especially ask_pipeworx and ask_pipeworx_beta (explicitly identical) and ask_pipeworx_grounded/deep_research/validate_claim for fact retrieval. Even with detailed descriptions, an agent could easily misselect among data-query tools or among the five Polymarket analysis tools.
Tool names mix verb-first (ask_pipeworx, compare_entities), noun-first (polymarket_edges, entity_profile), and single-word verbs (geocode, forget), with no strict verb_noun pattern. However, all names are snake_case and mostly descriptive, so the inconsistency is moderate.
36 tools is far beyond the typical well-scoped range of 3-15, and the feature set spans research, memory, subscriptions, prediction markets, and geo utilities. Many tools are meta-tools (discover_tools, suggest_questions) that could be consolidated, making the surface feel bloated.
For the apparently broad domain of data research and prediction markets, the toolset covers most needs with parallel research, grounding, claim verification, memory, and subscription lifecycle. Minor gaps exist—like a direct way to fetch arbitrary raw data or a unified list of all tools—but agents can generally work around them.