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. Description reinforces destructiveness and adds context about clearing sensitive data. No contradictions, but no additional behavioral traits beyond what annotations provide.
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 sentences, zero fluff, front-loaded with action and purpose. Every sentence adds value.
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?
With a single required parameter and no output schema, the description fully covers the tool's behavior. It provides sufficient context for correct usage.
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% with one parameter 'key' described as 'Memory key to delete'. Description does not add further meaning beyond the schema, so baseline score of 3 applies.
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?
Description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes from sibling tools 'remember' and 'recall' by mentioning pairing, making the purpose unambiguous.
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?
Explicitly lists use cases: stale context, task done, clear sensitive data. Also refers to alternatives 'remember' and 'recall', providing clear when-to-use guidance.
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 tool clusters have unclear boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route questions across the same 5,756-tool catalog, and ask_pipeworx_beta is explicitly identical to ask_pipeworx right now. The polymarket_* family also overlaps heavily (edges, arbitrage, fill_risk, kalshi_spread all surface tradeable discrepancies), and entity_profile/compare_entities/recent_changes all fan out to overlapping SEC/news/patent sources. Descriptions are detailed, but the set contains intentional near-duplicates that make selection genuinely ambiguous.
Naming follows no single convention: get_drivers/get_laps/get_meetings/get_sessions use verb_noun, polymarket_arbitrage/polymarket_edges are noun-phrase domain prefixes, pipeworx_feedback/pipeworx_trending use a vendor prefix, remember/recall/forget are bare verbs, and ask_pipeworx variants mix with action phrases like discover_tools, deep_research, and validate_claim. The inconsistency makes it harder to predict related tool names.
35 tools is heavy, and the count is severely mismatched to the server name 'Openf1': only 4 of 35 tools (get_drivers, get_laps, get_meetings, get_sessions) are actually F1-related, while the other 31 are a general-purpose Pipeworx data/prediction-market platform. The number itself could be reasonable for a broad data hub, but for an F1 server it is bloated with unrelated functionality.
For the stated F1 domain, the surface is severely incomplete: it covers meetings, sessions, drivers, and laps but lacks race results, qualifying results, standings, pit stops, or constructor data — major gaps for any F1 use case. The Pipeworx side is far more complete (query, research, entities, verification, memory, subscriptions), but that completeness doesn't serve the server's apparent purpose.