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 include destructiveHint: true and idempotentHint: true. The description confirms the destructive nature and adds context about clearing sensitive data, enhancing transparency beyond annotations.
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 no wasted words. The action is front-loaded, followed by usage context and related tools. Highly 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?
Given the single parameter, absence of output schema, and presence of annotations, the description fully captures the tool's purpose, usage, and pairing, 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?
With 100% schema coverage, the input schema already describes the 'key' parameter. The description does not add additional parameter details, so baseline score of 3 is appropriate.
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 action 'Delete a previously stored memory by key.' It specifies verb, resource, and method, distinguishing it from sibling tools like 'remember' and 'recall' by mentioning pairing.
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 provides when to use ('context is stale, task is done, clear sensitive data') and mentions related tools ('Pair with remember and recall'), offering clear guidance on 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.
The ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded trio is genuinely confusing — beta is explicitly identical to stable, and grounded differs only in output format, so agents will struggle to pick the right one. The six Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread, bet_research) also blur together despite distinct purposes, and ai_visibility_check vs scan_competitor_ai_presence overlap heavily.
Naming is largely consistent: snake_case throughout, with a strong verb-first pattern (list_subscriptions, resolve_entity, validate_claim, compare_entities, discover_tools) and clear domain prefixes for clusters (neso_, pipeworx_, polymarket_). The only inconsistency is the ask_pipeworx family, which differentiates by bare suffix (_beta, _grounded) rather than a descriptive verb.
35 tools is on the heavy side, but the server is a broad multi-domain data platform (SEC, FDA, FRED, NESO, Polymarket, npm, memory, subscriptions, discovery) where the count is arguably justified. Several tools could be consolidated — the three ask_pipeworx variants are redundant, and scan_competitor_ai_presence largely wraps ai_visibility_check — which would tighten the surface meaningfully.
Coverage is strong across the stated domains: lookups, deep research, entity resolution, claim verification, comparisons, memory lifecycle (remember/recall/forget), subscription lifecycle (subscribe/unsubscribe/list/recent_alerts), discovery (discover_tools, suggest_questions), feedback, and trending. Minor gaps exist (no direct document-fetch tool, scan_dependency is npm-only in v1) but nothing that creates a dead end.