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 disclose destructive (destructiveHint: true), read-only (readOnlyHint: false), and idempotent (idempotentHint: true) behavior. The description adds that it deletes a memory by key, which is the primary behavior, and mentions sensitive data context. However, it does not explain what happens if the key does not exist or whether deletion is irreversible, leaving some behavioral details implicit.
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, no fluff. The first sentence states the core purpose, and the second provides usage guidance and sibling pairing. Every word earns its place, and the description is appropriately front-loaded with the action.
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 single-parameter tool, the description is complete. It explains what it deletes, when to use it, and how it relates to remember and recall. The annotations cover safety and idempotency, and the schema covers parameters. No output schema exists, so no return-value explanation is needed.
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 already covers 100% of the parameters, with the 'key' property described as 'Memory key to delete.' The description only contributes the phrase 'by key,' which does not add meaningful semantics beyond the schema. Baseline score of 3 is appropriate since the schema does the heavy lifting.
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.' The resource is a memory, and the method is deletion via a specific key. It also distinguishes itself from sibling tools 'remember' and 'recall' by explicitly pairing with them, showing it is the complement for forgetting.
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 use cases: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names the alternatives 'remember' and 'recall' for storage and retrieval, respectively. It lacks an explicit when-not-to-use statement, but the alternatives are clear enough.
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.
There is significant overlap among many tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all serve query-answer purposes with subtle differences, and multiple polymarket tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) cover similar arbitrage/mispricing territory. Additionally, ai_visibility_check and scan_competitor_ai_presence clearly overlap, making it hard to pick the right one.
Tool names follow no consistent pattern. Some use a gh_ prefix (gh_get_file, gh_get_repo, etc.), others are descriptive phrases (ask_pipeworx, compare_entities, bet_research), and a few are plain verbs (remember, recall, forget, subscribe, unsubscribe). The mixed conventions and varied verb/noun styles make the set feel disjointed.
At 37 tools, the count is high but still within a usable range. However, the server is named 'Github_private' yet includes only 7 GitHub-specific tools and 30+ unrelated tools (Pipeworx data, Polymarket betting, memory, etc.). This suggests the server aggregates multiple unrelated domains, making the count feel bloated for its apparent GitHub purpose.
Given the server name, the GitHub tool surface is severely incomplete: there are no create/update/delete operations for repos, no PR creation or merging, no issue comments, no branches, and no search across repos. The Pipeworx side is fairly comprehensive, but the mismatch between the server name and the actual tool set leaves major gaps for expected GitHub workflows.