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. Description adds 'sensitive data' context but no further behavioral traits beyond what annotations provide.
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 action, no wasted words. Efficiently conveys purpose and usage.
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?
Simple tool with one parameter and no output schema. Description covers when and what, but lacks explicit return value info. Acceptable for destructive operation.
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?
Single parameter 'key' has 100% schema coverage with description 'Memory key to delete'. Description does not add extra 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' and specific resource 'memory by key'. Distinguishes from siblings 'remember' and 'recall' by name and pairing mention.
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. References paired tools 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 server mixes two Met-specific tools (get_artwork, search_artworks) with a large set of generic Pipeworx tools (ask_pipeworx, bet_research, etc.), making it unclear which tools actually relate to the Met museum. Agents will struggle to distinguish the domain-specific tools from the general data tools.
Tool names follow no consistent pattern: Met-specific tools use get_/search_/list_ prefixes, while Pipeworx tools use diverse patterns (ask_, bet_, compare_, discover_) and some use underscores while others lack verbs. The inconsistency increases cognitive load.
At 29 tools, the count is high but not unreasonable for a combined server. However, only 3 tools are Met-specific, so the count feels inflated by unrelated tools. A more focused Met server would have fewer tools.
For a Met museum server, the tool surface is severely limited: only search, get by ID, and list departments. Missing operations like filtering by artist, retrieving related objects, or accessing collection highlights. The domain coverage is incomplete.