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=true and idempotentHint=true, so the deletion behavior is covered. Description adds the 'clear sensitive data' use case but doesn't disclose additional behavioral traits beyond annotations. 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?
Two sentences, front-loaded with the core definition, then usage context. No redundancy or filler.
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 safety and idempotency, the description provides sufficient context: what, when, and how it relates to sibling tools. No output schema needed for such a simple operation.
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?
Input schema has 100% coverage with a clear description for 'key' parameter. Description adds no new parameter semantics 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?
Description uses specific verb 'Delete' plus resource 'previously stored memory by key', clearly distinguishing from siblings like remember (store) and recall (retrieve).
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: 'when context is stale, the task is done, or you want to clear sensitive data'. Also recommends pairing with remember and recall, providing workflow 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.
Several tool families overlap heavily: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded serve nearly the same routing purpose (beta explicitly 'currently matches ask_pipeworx exactly'), and the five polymarket_* tools plus bet_research create a dense cluster an agent must pick through. The descriptions are unusually detailed and do differentiate them, but the boundaries between the ask_pipeworx variants and between bet_research/polymarket_edges/arbitrage remain easy to misselect.
All names are lowercase snake_case and mostly follow verb_noun or domain-prefix patterns (ask_pipeworx, polymarket_edges, list_subscriptions, resolve_entity). Minor deviations exist: subjects and table_meta are bare nouns rather than verbs, the ask_pipeworx family uses an ask_ prefix while the closely related deep_research does not, and entity appears as both a prefix (entity_profile) and a suffix (resolve_entity).
34 tools is well above the 25-tool threshold for 'too many,' and the mismatch is sharpened by the server name 'Statfin Fi': only 3 of 34 tools (query_table, subjects, table_meta) actually relate to Statistics Finland, while the rest are a sprawling multi-domain platform covering prediction markets, AI visibility, npm packages, memory, and subscriptions. The count is appropriate for a general data platform but not for the apparent StatFin scope, making the surface feel bloated and unfocused.
The platform covers the full research lifecycle: discovery (discover_tools, suggest_questions), identifier resolution (resolve_entity), lookups (ask_pipeworx, entity_profile, compare_entities), verification (validate_claim, ask_pipeworx_grounded), monitoring (subscribe, recent_alerts, recent_changes), and memory (remember/recall/forget), with no obvious dead ends. Minor gaps exist β there is no keyword search across the StatFin catalog (browse-only via subjects), and one-off tools like generate_llms_txt and scan_dependency feel bolted on rather than part of a coherent domain.