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 destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds the context of clearing sensitive data but doesn't disclose additional behavior such as irreversibility or behavior for non-existent keys, though idempotency is already annotation.
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?
The description is two sentences, front-loaded with the action, followed by use cases and a pairing tip. Every word contributes; no fluff.
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, single-parameter destructive tool with comprehensive annotations, the description covers the action, when to use it, and how it relates to sibling tools. No output schema exists, so the lack of return-value documentation is acceptable.
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 single parameter 'key' is fully described in the schema as 'Memory key to delete' (100% coverage). The description echoes 'by key' without adding format or lookup details, so it adds minimal information 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 states exactly what the tool does ('Delete a previously stored memory by key') with a specific verb and resource, and it clearly differentiates from the related siblings 'remember' and 'recall' by positioning deletion as the inverse operation.
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?
It provides explicit when-to-use conditions ('context is stale, the task is done, or you want to clear sensitive data') and instructs pairing with 'remember' and 'recall', which implies the alternatives for storage and retrieval. It doesn't explicitly state when not to use it, but the conditions cover the main scenarios.
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 server is named 'chess', yet none of the 34 tools relate to chess. An agent looking for chess functionality would find all tools irrelevant. While individual tool descriptions are clear, the server's name creates a fundamental disambiguation problem: the tool set does not match the server's apparent purpose.
Tool names within the set follow a consistent snake_case pattern with descriptive verbs (e.g., ask_pipeworx, deep_research, resolve_entity). There are no mixed conventions. However, the server name 'chess' is completely inconsistent with the tool names, which all suggest data research rather than chess.
For a server named 'chess', 34 tools is wildly excessive. Even for a data research server, the count is high, but the server's name implies a narrow chess domain, making the count inappropriate. The tools cover broad topics like SEC filings, Polymarket, and weather, none of which belong in a chess server.
The server claims to be about chess, but there are zero chess-related tools. The tool set is completely incomplete for its stated purpose. As a data research server, completeness might be high, but that is irrelevant given the server name.