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 indicate destructiveHint=true and readOnlyHint=false, so the description's 'Delete' confirms mutation but doesn't add new behavioral details (e.g., permanence, undo capability). No contradiction, but value added is minimal beyond the structured 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?
Two concise sentences: first defines action, second lists use cases. No unnecessary words; information is front-loaded and well-structured.
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?
Given the tool's simplicity (single required param, no output schema), the description fully covers purpose, usage timing, and relationship to siblings. 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 has 100% description coverage for the sole parameter 'key' ('Memory key to delete'). The tool description does not add extra meaning or formatting guidance beyond the schema, so it meets the baseline without improvement.
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 'Delete a previously stored memory by key' with a specific verb and resource, and distinguishes from siblings 'remember' and 'recall', which serve complementary storage and retrieval functions.
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?
Provides explicit scenarios: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' Also references sibling tools for pairing, offering clear guidance on when to invoke this tool.
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.
Multiple tools occupy nearly identical roles: ask_pipeworx, ask_pipeworx_beta (explicitly identical right now), ask_pipeworx_grounded, and deep_research all answer research questions; polymarket_edges, bet_research, and polymarket_arbitrage overlap heavily on prediction-market opportunities; entity_profile, compare_entities, and recent_changes overlap on company research. The detailed descriptions help, but the clusters create real misselection risk.
Nearly all tools follow a readable snake_case convention, many with verb_noun structure (resolve_entity, list_subscriptions, validate_claim, scan_dependency). Minor deviations exist: tankerkoenig_stations_nearby plural vs tankerkoenig_station_details/prices singular, plus noun-style names like pipeworx_feedback and pipeworx_trending, but the overall pattern is predictable.
34 tools is heavy, and the problem is compounded by the server being named Tankerkoenig: only 3 of the 34 tools relate to German fuel prices while the other 31 are an unrelated Pipeworx/Polymarket/memory/subscription toolkit. This is a sprawling, unfocused surface rather than a well-scoped set.
For the nominal Tankerkoenig domain, stations_nearby + station_details + prices cover core lookups, though station search by name and price history are missing. For the broader bundled data/prediction-market domain, coverage is extensive but has notable gaps such as no trade execution, no general web search, and several redundant access paths that complicate the surface.