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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description aligns with these and adds context about clearing sensitive data and pairing with remember/recall. However, it does not disclose additional behavioral traits such as behavior when the key does not exist or confirmation of deletion, so it adds moderate 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 two sentences, front-loaded with the action, and contains no filler. Every word contributes to understanding the tool's purpose and usage.
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 one-parameter tool with annotations covering destructiveness and idempotency, the description is sufficiently complete. It states what the tool does, when to use it, and how it relates to siblings. It does not need to describe return values since no output schema exists, but could optionally mention what happens after deletion.
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 has 100% coverage of the single parameter 'key' with the description 'Memory key to delete'. The tool description repeats this by saying 'by key' but does not add extra meaning beyond what the schema already provides. 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 action ('Delete') and the resource ('previously stored memory'), with the specific mechanism ('by key'). It distinguishes itself from related sibling tools like remember and recall by naming them and positioning forget as their counterpart.
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 situations for use: stale context, task completion, or clearing sensitive data. It does not explicitly state when not to use it or offer alternative tools, but the pairing suggestion with remember/recall provides some comparative 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.
Several tools occupy overlapping boundaries: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicate query entry points (beta is currently identical), while ladder/standings, ai_visibility_check/scan_competitor_ai_presence, and polymarket_edges/polymarket_arbitrage also blur together. An agent would struggle to reliably pick the right tool without reading very long descriptions.
The vast majority of names are snake_case and many follow a readable verb_noun shape, such as resolve_entity, validate_claim, and list_subscriptions. However, the Squiggle/AFL tools are bare nouns (games, ladder, sources, standings, teams, tips), and the polymarket_* / pipeworx_* prefixes do not use one consistent verb style, so it is not a fully uniform convention.
37 tools is in the too-many band, and the sprawl is compounded by mixing unrelated domains under one server: AFL stats, a huge Pipeworx data-routing layer, prediction-market analytics, AI visibility checks, npm dependency review, and llms.txt generation. The set feels like several merged servers rather than one well-scoped MCP.
The query/research surface is broad and covers many subdomains, and the subscription lifecycle is reasonably complete with subscribe/list/unsubscribe/recent_alerts. However, pipeworx:// citation URIs are prominently returned but no tool fetches a cited record directly, the AFL side lacks player-level data, and subscriptions cannot be updated.