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, so the safety profile is known. The description adds usage rationales but no new behavioral details beyond what annotations and the schema provide. It does not contradict annotations, but the value-add is limited.
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 sentences that are direct and informative. The action is front-loaded, and each sentence earns its place: definition, when-to-use, and relationship to sibling tools. No wasted 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 single-parameter deletion tool with comprehensive annotations and full schema coverage, the description is complete. It explains purpose, usage context, and related tools without needing to describe return values (no output schema exists). The simple design is fully covered.
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 describes the single 'key' parameter with a clear description ('Memory key to delete'). The tool description repeats the concept 'by key' but adds no additional meaning beyond the schema. Baseline 3 is appropriate for 100% schema coverage.
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'), the resource ('previously stored memory'), and the mechanism ('by key'). It explicitly differentiates from siblings like 'remember' and 'recall' by focusing on deletion, and the pairing instruction further clarifies its complementary role.
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 provides explicit when-to-use scenarios: stale context, completed task, or clearing sensitive data. It does not explicitly state when not to use the tool, but the 'Pair with remember and recall' hint gives some context for alternative operations. Slightly below a perfect score due to lack of exclusions.
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.
Multiple tools have overlapping purposes: ask_pipeworx, ask_pipeworx_grounded, deep_research, and validate_claim all handle natural-language data queries, with ask_pipeworx_beta currently identical to ask_pipeworx. discover_tools and suggest_questions both exist to help agents find tools, and the five Polymarket tools have subtle, hard-to-distinguish boundaries. Agents will frequently select the wrong tool without careful reading.
Tool names are mostly lowercase snake_case with verb-noun structure (query_layer, search_datasets, resolve_entity), which is consistent and readable. However, some names break the pattern (entity_profile, layer_info, recent_changes, pipeworx_feedback) and the prefixes are not uniform. Still, the convention is predictable enough to navigate.
34 tools is a heavy count, and the vast majority are unrelated to the server's stated 'Arcgis Lacounty' purpose. Only three tools (search_datasets, query_layer, layer_info) serve the named GIS domain, while the rest form a sprawling collection of data-lookup, prediction-market, and utility tools. This is a severe scope mismatch.
The tool surface is severely incomplete for an ArcGIS LA County server: no layer listing beyond keyword search, no metadata endpoints, no editing, no spatial operations. The broader tool set lacks a coherent domain, making coverage impossible to assess beyond noting the glaring absence of core GIS functionality.