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.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint and idempotentHint, so the safety profile is known. The description does not add further behavioral details such as behavior when key is missing, irreversibility, or effects on other components; it only restates the delete action.
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 action first, then usage conditions. No redundancy, and every sentence 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?
For a single-parameter destructive tool with annotations covering risk, the description is sufficient: it defines the operation, use cases, and related tools. It could be slightly more complete by explaining the result of deleting a non-existent key, but the idempotent hint partially covers this.
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 covers the single 'key' parameter with description 'Memory key to delete' at 100% coverage. The description adds no additional meaning for the parameter beyond what schema already provides.
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 uses a specific verb ('Delete') and resource ('previously stored memory') with a clear key parameter, and distinguishes itself from siblings by explicitly pairing with '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?
It states explicit conditions when to use ('context is stale, task done, clear sensitive data') and identifies the complementary tools 'remember and recall' which serve the other storage operations.
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.
Most tools have fairly distinct action/resource targets and the descriptions carefully separate entry points like ask_pipeworx, deep_research, and ask_pipeworx_grounded. However, ask_pipeworx_beta is explicitly an identical clone of ask_pipeworx right now, and a few related pairs (ai_visibility_check vs scan_competitor_ai_presence, stat_ee_find_table fetch_latest vs estonia_average_wage) add ambiguity.
Names are consistently lowercase snake_case and verb-led names like resolve_entity, query_table, and suggest_questions are clear. But the set mixes conventions: bare nouns (subjects, recall, forget), adjective-noun phrases (recent_alerts, recent_changes), no-verb names (estonia_average_wage, table_meta), and multiple prefixes (pipeworx_*, polymarket_*, stat_ee_*). It is readable but not a single predictable pattern.
36 tools is well above the 15-tool threshold for a well-scoped server, and the set spans many unrelated domains: Estonian statistics, Pipeworx research, Polymarket betting, AI visibility, npm scanning, memory, and subscriptions. There is also clear redundancy (ask_pipeworx_beta duplicates ask_pipeworx, ai_visibility_check could be folded into scan_competitor_ai_presence). This feels scattered for a server named 'Stat Ee'.
For the broad data-research/agent-assistant purpose, key workflows are well covered: discovery/query/grounded/deep research, entity resolution/profile/compare/validate/recent changes, complete memory CRUD, subscription CRUD with alert feeds, and a full Polymarket edge/arb/fill-risk suite. The main gap is not missing operations within these workflows but rather the overall scope being too broad and unfocused.