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=true and idempotentHint=true, so the bar is lower. The description adds value by explaining the rationale for deletion (stale context, sensitive data) and implies irreversibility by using 'delete.' It does not contradict annotations and provides useful behavioral context beyond the structured hints.
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 coherent sentences deliver all essential information. The first sentence states the action and scope, the second provides usage guidance and tool pairing. No filler words or redundant repetition of schema information.
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 single-parameter delete operation with full schema coverage and annotations, the description is complete. It explains what, when, and how to use, plus complementary tools. No output schema exists, but the return value is not critical for a destruction 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?
The schema covers the only parameter 'key' with a clear description ('Memory key to delete'), giving 100% coverage. The description reinforces the role of the key but adds no new parameter-level detail. Baseline 3 is appropriate since the schema handles the heavy lifting.
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 opens with a specific verb+resource: 'Delete a previously stored memory by key.' This clearly distinguishes the tool from siblings like remember and recall, which store and retrieve memories respectively. The addition of 'previously stored' and 'by key' scopes the operation precisely.
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: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also suggests complementary tools with 'Pair with remember and recall,' providing clear context for when this tool is appropriate versus 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.
Several tools are easy to confuse: ask_pipeworx_beta is currently identical to ask_pipeworx, deep_research overlaps heavily with ask_pipeworx/ask_pipeworx_grounded, and the six polymarket_* tools have closely related purposes. ai_visibility_check and scan_competitor_ai_presence also overlap, making selection error-prone.
Almost all tools use lowercase snake_case and mostly follow a verb_noun pattern (query_layer, resolve_entity, scan_dependency, validate_claim). A few noun-style names like entity_profile, layer_info, and pipeworx_trending deviate slightly, but the overall convention is predictable.
34 tools is well past the heavy threshold, and the server is named 'Arcgis Charlotte' while only three tools actually relate to ArcGIS. The rest form a sprawling Pipeworx research, prediction-market, subscription, and memory toolkit, which creates a severe scope mismatch.
For the Pipeworx data side the surface is quite thorough, but for the declared ArcGIS Charlotte purpose it is thin: search_datasets, layer_info, and query_layer provide read-only access with no update/delete, analysis, or dataset management. The tool set therefore has a significant gap relative to its stated domain.