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?
The annotations already declare destructiveHint=true and idempotentHint=true, and the description adds useful context about when deletion is appropriate without contradicting the annotations. It doesn't specify error handling for missing keys, but this is minimal given the schema and 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?
Three concise sentences, with the action front-loaded and no filler. Every sentence contributes to understanding the tool's purpose, usage, and relationships.
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?
The tool is simple (single parameter, no output schema), and the description plus annotations cover purpose, usage, and safety completely. No gaps remain.
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%, so the schema fully documents the 'key' parameter. The description adds no extra parameter semantics beyond saying 'by key', but with full schema coverage, a baseline of 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 states a specific action ('Delete a previously stored memory by key') and identifies the resource (memory) and scope (by key). It clearly distinguishes the tool from siblings like remember and recall.
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 states when to use the tool ('context is stale, the task is done, or you want to clear sensitive data') and references sibling tools (remember, recall) for pairing, providing clear guidance on alternatives.
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 have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded differ only in mode, and the polymarket_* cluster (polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread) all target prediction-market analysis with fuzzy boundaries. The presence of ai_visibility_check and scan_competitor_ai_presence, plus discover_tools and suggest_questions, adds further ambiguity about which tool to select first.
Names are all snake_case but follow mixed conventions: verb_noun (list_feeds, read_feed, fetch_feed, validate_claim) coexists with noun_phrase (entity_profile, recent_changes, polymarket_edges) and prefix-grouped names (ask_pipeworx*, polymarket_*). While subgroups are internally consistent, the overall set lacks a unified pattern, though it remains readable.
34 tools is well above the 25+ threshold for too many, and the count is especially inappropriate for a server named 'Sports Feeds' — most tools are generic data-research or meta-tools (subscriptions, memory, feedback, discovery) unrelated to sports feeds. The bloat suggests the server is actually a broad Pipeworx gateway, not a focused sports feeder.
For a sports-feeds server, only list_feeds, read_feed, and fetch_feed address the core domain, and there is no feed search, categorization beyond a simple list, or sports-specific analytics. While the general research surface (SEC, FDA, economics, prediction markets) is fairly comprehensive, it is misaligned with the stated server purpose, leaving the actual sports-feed functionality thin and with obvious gaps.