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 indicate destructiveHint=true and idempotentHint=true, so the description's job is light. The description adds 'delete' which aligns, but does not elaborate on whether deletion is permanent, what happens if the key doesn't exist, or other side effects. With annotations covering the core traits, a score of 3 is appropriate.
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, zero fluff, front-loaded with action and usage conditions. Every word adds value.
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 parameter, no output schema, clear annotations), the description is fully complete. It covers purpose, usage context, and relationships to sibling tools.
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 mentions 'by key' but adds no additional meaning beyond the schema. Baseline 3 is correct.
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.' It identifies the specific resource (memory) and the operation (delete), distinguishing it from sibling tools 'remember' and 'recall' which handle storage and retrieval.
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 guidance on when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data.' It also suggests pairing with 'remember' and 'recall', informing the agent of 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.
Multiple tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all answer questions or discover data via the same routing engine, with ask_pipeworx_beta explicitly stated to be identical to ask_pipeworx. Polymarket tools (arbitrage, edges, edge_tracker, fill_risk) also blur together, and ai_visibility_check overlaps with scan_competitor_ai_presence.
Some clusters are consistent (chargebee_list_*/chargebee_get_*, polymarket_*, pipeworx_*), but the set mixes snake_case with varying verb styles and many unprefixed tools (remember, recall, forget, subscribe, unsubscribe, validate_claim). The 5 Chargebee tools use a clean prefix while the other 31 tools follow several different conventions, making the overall pattern unpredictable.
36 tools is excessively heavy for a server named Chargebee, especially since only 5 tools actually relate to Chargebee. The remaining 31 tools form a broad Pipeworx/prediction-market/utility toolkit that has little connection to the server's apparent billing purpose, making the count feel bloated and unfocused.
The Chargebee-specific surface is severely incomplete: it only supports reading customers, subscriptions, and invoices, with no create, update, delete, payment, dunning, coupon, or plan-management operations. The rest of the tools belong to unrelated domains, so the set as a whole has no coherent lifecycle coverage and would leave agents unable to perform even basic Chargebee management tasks.