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 declare idempotentHint=true and destructiveHint=true. The description adds usage context but not additional behavioral traits like what happens if the key doesn't exist or if the deletion is permanent.
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, front-loaded with the action, no redundant words. Every sentence earns its place.
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 parameter, strong annotations, and no output schema, the description is nearly complete. It could mention that no return value is expected, but not necessary.
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 schema has 100% coverage for the single parameter with description, so baseline is 3. The description does not add extra semantic meaning beyond the 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?
The description clearly states the action ('delete'), the resource ('memory'), and the means ('by key'). It distinguishes from sibling tools 'remember' and 'recall' by specifying deletion vs. storage and retrieval.
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 explicitly lists when to use the tool (context stale, task done, clear sensitive data) and recommends pairing with 'remember' and 'recall', providing 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.
Each tool has a clearly distinct purpose, even within clusters like Pipeworx queries (ask_pipeworx vs ask_pipeworx_grounded vs deep_research) and Polymarket tools (bet_research, arbitrage, edges, etc.). Overlap is minimal and explicitly addressed in descriptions.
All tool names use snake_case, and most follow a consistent verb_noun pattern (e.g., ask_pipeworx, compare_entities, resolve_entity). Exceptions like remember, reverse are still single words in the same style.
32 tools is on the high side but justified by the wide scope: data querying, betting, memory, subscriptions, and utilities. Each tool earns its place, and the count is not excessive given the breadth.
The tool set covers the core workflows of querying structured data, comparing entities, validating claims, scanning dependencies, and monitoring, with few gaps (e.g., no direct data visualization). Minor gaps exist but are manageable.