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?
Annotations already provide destructiveHint=true and idempotentHint=true. Description adds context about use cases but no extra behavioral details. Consistent, no contradiction.
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 with no wasted words. Front-loaded purpose, then usage guidance.
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 tool with one required parameter and no output schema, the description fully covers purpose, usage, and parameter meaning. References siblings for context.
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% and describes 'key' as memory key. Description adds no additional semantics beyond schema.
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?
Clear verb 'delete' with specific resource 'memory by key'. Distinguishes from siblings by naming '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: stale context, task done, clear sensitive data. Mentions pairing with remember and recall.
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.
The ENTSO-E energy tools are clearly distinct, but the Pipeworx half contains overlapping query modes: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, and ask_pipeworx/ask_pipeworx_grounded/deep_research/validate_claim all route natural-language questions to the same underlying catalog. The Polymarket tools also blur edge detection, arbitrage, fill-risk, and persistence tracking, so an agent can easily select the wrong one.
The five ENTSO-E tools use a clean snake_case noun pattern, but the rest mix brand verbs (ask_pipeworx, bet_research), bare memory verbs (remember, recall, forget), and polymorphic prefixes (polymarket_*), with inconsistent suffixes like beta, grounded, and kalshi_spread. There is no server-wide predictable naming convention.
36 tools is too many for the apparent scope, and the server name promises ENTSO-E while only 5 of 36 tools serve that domain. Even viewed as a general data utility, the count is heavy and includes duplicate query modes, though individual clusters do have some purpose.
For an ENTSO-E server, the five energy tools cover the basics (generation, load, price, flow, capacity) but omit common datasets like generation forecasts, balancing/imbalance prices, and outages. The unrelated Pipeworx tools add broad research, memory, and subscription coverage, but the overall surface feels like a general-purpose assistant with an energy add-on rather than a complete energy domain.