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. The description adds the specific resource destroyed (a memory by key) and the sensitive-data clearing use case, which goes beyond the annotation hints. 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?
Three concise sentences that efficiently cover the action, usage guidance, and relationship to sibling tools. No redundant or filler content.
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 one-parameter destructive operation, the description fully covers purpose, usage conditions, and tool relationships. Annotations handle safety hints, and the schema covers parameter detail, leaving no significant gaps for an agent to select and invoke the tool.
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 input schema fully covers the 'key' parameter with a clear description. The tool description only mentions 'by key' without adding new semantic detail, so it meets the schema-coverage baseline but does not exceed it.
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 tool deletes a previously stored memory by key, using a specific verb and resource. It also distinguishes itself from siblings by mentioning pairing with 'remember' and 'recall', making its role in the memory workflow unambiguous.
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 usage conditions: use when context is stale, the task is done, or when clearing sensitive data. It also indicates alternatives by pairing with 'remember' and 'recall', signaling when not to use this tool.
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.
Many tools overlap in purpose: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all provide data retrieval with subtle differences. The Polymarket suite (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) and AI visibility tools (ai_visibility_check, scan_competitor_ai_presence) also have fuzzy boundaries. While some tools are clearly distinct, the overall set has significant ambiguity that could lead to misselection.
Tool names mix conventions: some are verb_noun (search_networks, compare_entities, remember, forget), others are noun_compound (entity_profile, polymarket_edges, ask_pipeworx), and a few are verb-only (recall, forget). The pattern is inconsistent, with no clear naming strategy across the tool surface.
With 34 tools, the server is heavily overloaded. While it serves as a general data platform, many tools are meta-level (discover_tools, suggest_questions) or peripheral (subscriptions, memory). The count feels excessive for the core purpose, and many tools could be consolidated or removed.
Despite the server name 'Peeringdb', only three tools (search_networks, search_facilities, search_exchanges) directly serve that domain. The vast majority of tools cover unrelated areas (Pipeworx data, Polymarket betting, AI visibility, memory, subscriptions). For the declared purpose of PeeringDB, the surface is severely incomplete—missing common operations like retrieving network details, viewing IX members, or managing peering policies.