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 and idempotentHint=true, and the description adds context about the nature of the data (sensitive) and the lifecycle of memories. While it doesn't elaborate on idempotency or missing keys, it complements the annotations well without contradicting them.
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 the primary action front-loaded and usage guidance immediately after. Every word contributes value, making it highly concise and well-structured.
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 delete tool with one parameter and annotations covering safety, the description is complete. It covers purpose, usage conditions, and related tools, and the lack of output schema is not a gap given the straightforward nature of the 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?
Schema coverage is 100% with a clear description for the key parameter. The description reiterates 'by key' but adds no additional semantic detail beyond the schema, so the baseline 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 tool deletes a previously stored memory by key, using a specific verb and resource. It distinguishes from siblings like remember and recall by explicitly naming them as partners for other operations.
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?
It provides explicit when-to-use guidance: stale context, task completion, or clearing sensitive data. The mention of pairing with remember and recall implies when to use alternatives, giving clear usage 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.
The ArcGIS tools (query_layer, layer_info, search_datasets) are clearly distinct, but the Pipeworx family has heavy overlap: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and discover_tools can all appear as plausible entry points for a similar data lookup task. The memory and subscription tools are well separated, but the router-style tools create real ambiguity.
Almost all tools use lowercase snake_case names with a verb-first pattern (ask_pipeworx, query_layer, subscribe, remember) or clear noun descriptors (entity_profile, layer_info, polymarket_edges). A few names are more cryptic (recall, forget, resolve_entity) but they still follow the same style. No mixed camelCase or inconsistent separators.
34 tools is well beyond what the apparent ArcGIS Washington County purpose needs; only three tools actually concern GIS data. The rest are a broad Pipeworx research suite, memory, subscriptions, feedback, and AI-visibility probes. This makes the surface feel like two or three unrelated servers grafted together rather than one scoped package.
For the ArcGIS slice, you can discover, inspect, and query layers, but there is no write or create capability, no field-wise editing, no map/feature export, and no feature-level CRUD. The Pipeworx data side is more comprehensive, but the overall server confuses its purpose. The mixed-domain coverage leaves the GIS part only a thin slice of the offered features.