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 provide destructiveHint=true and idempotentHint=true. Description adds minimal extra behavioral context beyond 'delete' and 'by key'. Missing details on behavior when key not found or if deletion is reversible.
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, front-loaded with action and immediately followed by usage guidance. No wasted words.
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 tool simplicity and high parameter coverage, most context is covered. Lacks explanation of return value or confirmation, but annotations compensate for destructive nature.
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 clear parameter description 'Memory key to delete'. The description adds no additional semantic value beyond the schema; baseline 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?
Description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes itself from sibling tools 'remember' and 'recall' by being the delete counterpart.
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 states when to use: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' Does not provide explicit when-not-to-use but pairs with siblings for context.
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.
Many tools have overlapping purposes, especially the Pipeworx query tools (ask_pipeworx, ask_pipeworx_grounded, deep_research) which all serve similar data retrieval needs. Additionally, entity_profile, compare_entities, and recent_changes overlap in providing company information. Polymarket tools also have overlapping analysis functions. This can cause confusion for agents.
Tool names are inconsistent in style and convention. Some use underscores (ai_visibility_check, ask_pipeworx), others are single words (forget, recall), and many lack a clear verb_noun pattern (pipeworx_feedback, polymarket_edges). This mixture of naming conventions reduces predictability.
With 32 tools, the count is on the higher side but appropriate given the broad scope covering multiple domains (Pipeworx data, Polymarket betting, ACLED events, npm scanning, memory, etc.). However, some areas have only one or two tools, which feels sparse, and the overall set could be trimmed or better organized.
The tool set covers many domains but has notable gaps. For ACLED, only search and count tools exist without any update/delete capabilities. For Pipeworx, the tools are heavily read-focused with no apparent write operations. The broad scope makes completeness hard to assess, but some obvious lifecycle operations are missing.