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. The description's 'Delete' aligns with destructive behavior, but adds no new behavioral traits beyond the annotation context. It mentions clearing sensitive data, which provides some additional context, but overall does not significantly enhance transparency 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?
The description is two sentences long, concise, and front-loaded with the core action. Every sentence adds value, and there is no extraneous information.
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?
Given the tool's simplicity (one required param, no output schema, annotations present), the description adequately covers the purpose and usage context. It lacks explicit mention of the return value or success/failure indicators, but that is not required per evaluation rules. Annotations fill in the safety profile, making it fairly complete.
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?
The input schema has 100% coverage for the single parameter 'key', with a description 'Memory key to delete'. The tool description does not add any further semantics about the parameter (e.g., format, constraints). Since schema coverage is high, a baseline of 3 is appropriate.
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 tool's purpose: 'Delete a previously stored memory by key.' It specifies the verb (delete) and resource (memory by key), and distinguishes 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?
The description provides explicit guidance on when to use the tool: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also mentions pairing with remember and recall. Although it doesn't explicitly state when not to use it, the guidance is clear and helpful.
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 tools overlap heavily: ask_pipeworx and ask_pipeworx_beta are described as currently identical, and deep_research/ask_pipeworx plus the many polymarket_* tools have adjacent intents that are easy to confuse. scan_competitor_ai_presence also directly wraps ai_visibility_check, so an agent can easily select the wrong tool for the same task.
Names are consistently snake_case, but the convention is mixed: some are verb-first (query_subgraph, introspect_schema, validate_claim), some are noun-first (entity_profile, polymarket_edges, pipeworx_trending), and some are bare verbs (remember, recall, forget). The repeated prefixes help, but there is no single predictable naming pattern across the set.
With 33 tools, this exceeds a reasonable single-server footprint, and the scope sprawls across data routing, prediction markets, AI visibility, npm dependencies, llms.txt generation, memory, and subscriptions. Many tools feel like separate mini-applications rather than one coherent toolkit for The Graph.
The Pipeworx data-research and prediction-market side is well covered with lookup, grounded answers, research, comparison, profiles, claims, subscriptions, and memory. However, the server's apparent namesake, The Graph, is thin: only query_subgraph and introspect_schema exist, with no subgraph discovery, status, or management tools.