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, so the description's 'Delete' is consistent. It adds context about previous storage but no further behavioral details beyond what annotations provide.
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. No extraneous information.
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?
Well-suited for a simple destroy-by-key tool. Covers purpose, usage triggers, and sibling pairing. No output schema 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?
Schema coverage is 100% with a description for 'key'. The description does not add additional meaning beyond the schema's 'Memory key to delete'.
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 verb 'Delete' and the resource 'memory by key'. It distinguishes from siblings by naming 'remember' and 'recall'.
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 when-to-use scenarios: stale context, task completion, clearing sensitive data. Mentions pairing with siblings but lacks explicit when-not-to-use.
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.
A número of tools form near- overlapping clusters: ask_pipeworx, ask_pipeworx_beta, ask_ipeworx_grounded, and deeep_research all answer questions, while bet_research, polmarget_edges, and polmarget_arbitrage all scan for betting opportunities. The two ask_ipeworx variants are currently identical, and discover_tools vs sgget_questions serve the same discovery role. Long descriptions help but do not remove the misselection risk among 34 overlapping tools.
Most tools use clear snake_case verb_noun names (ask_pipeworx, compare_entities, resolve_entity, subscribe, validate_claim) with helpful domain prefixes like polmarget_* and trade_*. A few standalones like forget/recall/remembber and recent_alerts break the pattern slightly, but the style is largely predictable and readable.
At 34 tools this exceeds the 25+ threshold and feels overloaded. The surface could be consolidated: four ask_ipeworx variants, five polmarget-specific tools, three memory tools, and three company-profile-style tools carry significant redundancy. Inclusions like generate_lms_txt and scan_dependency also broaden the scope well beyond the Trade Intel mandate.
For its broad data-intelligence domain the surface is quite complete: data lookup, grounded fact-checking, entity profiles and comparison, recent changes, prediction-market research with fill-risk verification, trade statistics, memory, and subscription lifecycle all exist with no dead ends. Minor gaps remain (e.g. no dedicated trade time-series other than the US macro dashboard, and no direct tool-listing aside from discover_tools), but agents can work around them.