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 (mutation) and idempotentHint=true. Description adds context about clearing sensitive data and pairs well, but does not contradict annotations. Adds moderate value beyond structured fields.
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 with zero waste: first sentence states purpose, second provides usage guidance. Front-loaded and efficient.
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 tool with one required parameter and comprehensive annotations, the description is complete. It covers purpose, usage timing, and related tools, leaving no gaps.
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% and includes a description for the 'key' parameter. Description does not add additional parameter semantics beyond what the schema provides, meeting baseline.
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.' The verb 'delete' and resource 'memory' are specific. It distinguishes from sibling tools 'remember' and 'recall' by being the deletion 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 says when to use: 'when context is stale, the task is done, or you want to clear sensitive data.' Also directs to pair with 'remember' and 'recall,' providing clear 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.
Several tools have heavily overlapping or explicitly duplicate purposes: ask_pipeworx_beta is described as currently identical to ask_pipeworx, while ask_pipeworx, ask_pipeworx_grounded, deep_research, and validate_claim all route natural-language queries to similar lookup pipelines. The Polymarket tools also blur together (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk), and scan_competitor_ai_presence is just a wrapper around ai_visibility_check.
There are readable verb-led names like search_publications, get_project, resolve_entity, and validate_claim, but the set mixes conventions with noun-phrase names like entity_profile, recent_alerts, polymarket_edges, and pipeworx_trending. The lack of a single verb_noun pattern makes the surface feel inconsistent, though each family is internally recognizable.
At 37 tools, this is well beyond the 25+ threshold where an agent starts paying significant selection and context cost. The broad domain could justify some breadth, but many tools are meta-wrappers or near-duplicates (ask_pipeworx_beta, compare_entities, entity_profile, deep_research) that inflate the count.
Within its main subdomains, the surface is fairly complete: OpenAIRE search has matching get_project/get_research_product retrieval, memory has remember/recall/forget, subscriptions have subscribe/unsubscribe/list/recent_alerts, and there are discovery/onboarding helpers like suggest_questions and discover_tools. Minor gaps exist (e.g., no direct generic Polymarket market quote tool, no memory update besides overwrite), but no major workflow is a dead end.