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?
The description does not add behavioral information beyond what annotations already provide. Annotations declare destructiveHint=true and idempotentHint=true, and the description simply says 'Delete' without elaborating on behavior like error handling or idempotency. No contradiction.
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 extremely concise: two sentences plus a pairing hint. The primary purpose is stated first, making it front-loaded with the most important information. No unnecessary 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?
For a simple tool with one parameter, no output schema, and clear annotations, the description is complete. It covers purpose, usage guidelines, and pairing with siblings, leaving no ambiguity.
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 the single 'key' parameter already described as 'Memory key to delete'. The description does not add any additional semantic information beyond the schema, earning the baseline score of 3.
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 it deletes a stored memory by key. It distinguishes from sibling tools 'remember' and 'recall' by explicitly mentioning them in the pairing hint.
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: when context is stale, task is done, or to clear sensitive data. It also suggests pairing with remember and recall, making the usage context clear.
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 are three ask_pipeworx variants that overlap heavily, plus five polymarket_* tools scanning similar market edges, and meta-tools like discover_tools, suggest_questions, and deep_research that blur together. ai_visibility_check and scan_competitor_ai_presence also overlap. The Cloudflare Radar tools are distinct, but they are a small minority in a sea of overlapping data/prediction-market tools.
Most tools use snake_case, but the pattern is inconsistent: some are verb_noun (list_subscriptions, resolve_entity, scan_dependency), some are noun_phrase (bgp_leaks, internet_quality, radar_domain_rank), and some use vendor-prefixed naming inconsistently (ask_pipeworx vs pipeworx_feedback vs pipeworx_trending). It is readable but not predictable.
37 tools is heavy for any single server, and the collection spans unrelated domains: Cloudflare Radar, Pipeworx data lookup, Polymarket betting, memory, subscriptions, and npm scanning. The count feels like a bundled platform rather than a focused tool set, and many tools could be split into separate servers.
The Pipeworx data-research side is quite complete (ask, grounded, deep_research, entity_profile, compare_entities, validate_claim, resolve_entity, discover_tools, recent_changes), and the prediction-market side has good coverage (edges, arbitrage, fill risk, cross-venue spread, tracking). However, the Cloudflare Radar portion is thin—only six tools cover a service known for many more traffic/attack/outage metrics—and the overall surface has no cohesive domain to judge completeness against.