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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, so the safety profile is clear. The description adds the context of clearing sensitive data and pairing with related tools, but does not disclose what happens if the key does not exist or whether deletion is permanent. Given the annotations cover the main behavioral traits, a score of 3 is appropriate.
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 three sentences, each serving a purpose: the first states the action, the second gives usage scenarios, and the third relates it to sibling tools. It is front-loaded with the core purpose and contains no unnecessary wording.
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 parameter and no output schema, the description is complete. It explains what the tool does, when to use it, and how it relates to other memory tools. Annotations cover the destructive and idempotent nature, so no additional context is needed.
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 schema description covers 100% of the single parameter 'key' with 'Memory key to delete'. The description's phrase 'by key' mirrors the schema without adding extra detail on key format or semantics, so it does not go 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 uses the specific verb 'Delete' and identifies the resource as 'a previously stored memory by key'. It clearly distinguishes itself from siblings like 'remember' and 'recall' by noting 'Pair 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?
The description explicitly states when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier'. It also mentions pairing with remember and recall, but does not explicitly mention when not to use it or alternatives beyond the pairing.
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 are clearly distinct, but there are several overlapping clusters: ask_pipeworx and ask_pipeworx_beta are near-duplicates today, the Polymarket tools (edges, arbitrage, fill_risk, bet_research) have partially overlapping discovery purposes, and ai_visibility_check vs scan_competitor_ai_presence overlap on single vs multi-entity checks. These overlaps create real misselection risk, though the rest of the set splits cleanly.
All names are snake_case and readable, but conventions vary noticeably: verb_noun for actions (check_ip, report_ip, list_subscriptions), domain-prefixed nouns for the Polymarket cluster (polymarket_edges, polymarket_arbitrage), and brand-prefixed meta tools (ask_pipeworx, pipeworx_feedback). Subfamilies are internally consistent, but the overall set mixes patterns.
34 tools is already past the heavy threshold, but the bigger issue is the server name: Abuseipdb should have a handful of IP-abuse tools, yet only 3 of 34 actually relate to AbuseIPDB. The remaining 31 tools form an unrelated Pipeworx/Polymarket/memory suite, making the count wildly inappropriate for the apparent purpose.
For the declared AbuseIPDB domain, only check, report, and blacklist are covered; obvious gaps remain like removing/clearing a false report, bulk IP checks, or category metadata. The broader set is a grab bag of unrelated capabilities, so no single domain gets complete lifecycle coverage, and the nominal AbuseIPDB surface is thin and diluted.