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 indicate destructiveHint=true and readOnlyHint=false. The description confirms deletion but adds no new behavioral context beyond what annotations and schema 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?
The description is two sentences long, directly states the purpose and usage, and is front-loaded with the core action. 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 required parameter and no output schema, the description adequately covers purpose, usage, and context. It pairs with siblings and provides complete guidance.
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?
The single parameter 'key' is fully described in the schema ('Memory key to delete'). Schema coverage is 100%, so the description adds no additional semantic value beyond the schema.
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) and the resource (a previously stored memory by key). It distinguishes from sibling tools like remember and recall by specifying deletion.
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 lists use cases (stale context, task done, clear sensitive data) and recommends pairing with siblings (remember, recall), providing clear when-to-use guidance.
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 tools have genuinely unclear boundaries: ask_pipeworx and ask_pipeworx_beta are currently identical in behavior, and the polymarket_edges / polymarket_arbitrage / polymarket_kalshi_spread trio all scan for mispricings with overlapping descriptions. The rich usage notes help, but they cannot fully rescue a set where two tools literally do the same thing right now.
The majority of tools use readable snake_case, but conventions are mixed: verb-first names (get_index_data, resolve_entity, validate_claim) sit alongside noun-first names (catalog_browse, index_catalog, entity_profile, bet_research), standalone verbs (remember, forget, subscribe), and adjective-led names (recent_alerts, deep_research). The pattern is predictable within clusters but not uniform across the set.
35 tools is well above the comfortable range, and the set spans many unrelated domains—CBS Israel statistics, Pipeworx data routing, Polymarket betting, memory, subscriptions, npm dependency scanning, and AI visibility checks. Even if each tool has a purpose, the surface is bloated and poorly scoped for a server named 'Cbs Il'.
For a general data-access gateway, the set covers the major workflows: routing questions, grounded verification, deep multi-source research, entity profiles, comparisons, subscriptions, memory, and tool discovery. Minor gaps exist, such as no direct raw-record fetch without routing and no keyword search over the CBS catalog, but agents can work around these.