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 indicate destructiveHint=true and readOnlyHint=false. The description adds 'Delete' which confirms destructiveness but does not elaborate on idempotency, error handling, or effects of deleting a non-existent key. The description adds minimal value beyond annotations.
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 a single sentence plus one usage sentence, with no wasted words. The key purpose is front-loaded. Every sentence is necessary.
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 no output schema, the description provides purpose, usage context, and sibling relationships. It lacks details on return value or confirmation, but these are often implicit for delete operations. Slightly incomplete but adequate.
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% for the single parameter 'key', with a basic description. The tool description does not add further meaning about what constitutes a valid key or how to obtain it. Baseline of 3 is appropriate since schema covers the parameter completely.
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') and the resource ('previously stored memory by key'), and distinguishes it from sibling tools 'remember' and 'recall' by mentioning them for pairing.
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 lists when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. It also suggests pairing with 'remember' and 'recall', providing context on alternatives. However, it does not state when NOT to use.
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 have detailed guidance, but several sets blur together: ask_pipeworx_beta is currently identical to ask_pipeworx, polymarket_edges and polymarket_arbitrage both scan for opportunities, and discover_tools/suggest_questions both serve discovery. The descriptions are strong enough to prevent frequent misselection, but the boundaries are not always crisp.
Names are consistently snake_case, but the stylistic pattern is mixed: verb_noun names like generate_llms_txt and list_subscriptions sit alongside bare verbs like remember/forget and noun-phrase names like entity_profile, recent_alerts, and polymarket_arbitrage. Prefixes like polymarket_*, pipeworx_*, and regrid_parcel_* add some order, but the set is not uniform.
33 tools is well above the point where a tool set remains easy to navigate, and several tools are near-duplicates or wrappers: ask_pipeworx_beta duplicates ask_pipeworx, scan_competitor_ai_presence is a wrapper around ai_visibility_check, and the prediction-market scanners overlap. The broad domain explains some of the bulk, but the surface still feels overweight.
The server covers a wide range of workflows: lookup, deep research, claim validation, entity profiles, comparisons, subscriptions, memory, prediction-market analysis, and parcel lookup. However, the Regrid parcel side is thin with only address and point lookup, and there is no direct tool for parcel-ID/owner/sales/tax queries. These are real gaps, though the universal router helps agents work around them.