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 and idempotentHint=true, and the description does not contradict these. It adds contextual value by noting the memory was 'saved earlier' and that it can clear 'sensitive data,' which reinforces the irreversible nature. It doesn't discuss missing-key behavior or return values, but given the annotations, this is sufficient.
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 exactly two sentences, front-loaded with the action, and every word contributes. It avoids fluff or repetition while covering purpose, usage, and sibling context.
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 tool with no output schema and strong annotations, the description is complete. It explains the operation, when to use it, and how it relates to related tools, giving the agent all necessary context to invoke it correctly.
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 covers 100% of the single parameter with 'Memory key to delete.' The description adds 'by key' and 'previously stored,' but these merely restate the schema rather than providing additional semantic details about format, constraints, or behavior. Baseline of 3 is appropriate for full 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 opens with 'Delete a previously stored memory by key,' which uses a specific verb and resource, exactly stating the operation. It clearly distinguishes from siblings like 'remember' and 'recall' by its explicit pairing and the 'previously stored' qualifier.
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 guidance: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names companion tools 'remember' and 'recall,' which helps an agent choose among related memory operations.
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 blurred boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all route questions to overlapping data pipelines, and the Polymarket family (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread) heavily overlaps in purpose. Individual descriptions are detailed, but an agent must read long text to avoid misselection, especially when the three anime-quote tools are surrounded by unrelated tool families.
Most tools use snake_case and many begin with verbs (ask_, search_, resolve_, scan_, compare_, validate_), but several are noun-first or noun-phrase names like entity_profile, bet_research, random_quote, recent_alerts, recent_changes, and pipeworx_trending. There is no chaotic camelCase/snake_case mix, but the convention is not applied consistently enough for a predictable pattern.
34 tools is heavy for any single-purpose server, and the vast majority have nothing to do with anime quotes—they are Pipeworx data tools, prediction-market tools, subscription tools, memory tools, and AI-audit tools. For a server named animequotes, only random_quote, search_by_anime, and search_by_character fit the stated purpose, making the count wildly disproportionate.
For the apparent anime-quote domain, random_quote, search_by_anime, and search_by_character cover basic lookup but leave notable gaps: no search by quote text, no quote-by-id fetch, no ability to list all series or characters, and no pagination or metadata browsing. The unrelated tools do not fill these gaps, so the anime-quote surface is functional but incomplete.