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 include destructiveHint=true and idempotentHint=true. Description adds context about memory deletion but does not significantly extend beyond the annotations. Acceptable for a simple operation.
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, concise and front-loaded with action and resource. No superfluous words.
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 deletion tool with one parameter and no output schema, the description covers purpose, usage scenarios, and relation to siblings. Missing return behavior but acceptable for this 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 the schema provides clear description for the key parameter. Description adds 'previously stored' but doesn't add essential new 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 'Delete a previously stored memory by key,' using a specific verb (delete) and resource (memory). It distinguishes from siblings like 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 provides scenarios for use: stale context, task done, or clearing sensitive data. Also advises pairing with remember and recall. Lacks a direct 'when not to use' but is sufficiently clear.
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.
Several tools are near-identical: ask_pipeworx and ask_pipeworx_beta are explicitly the same right now, and the three ask_pipeworx variants plus deep_research all route the same underlying catalog. The six polymarket_* tools also have heavily overlapping purposes, requiring deep reading to choose correctly. Most other tools are distinguishable, but these clusters create real misselection risk.
The set is uniformly snake_case and mostly descriptive, with consistent micro-families like remember/recall/forget and polymarket_*. However, there is no single convention across the server: verb_noun names (ask_pipeworx, list_subscriptions) mix with noun-first names (entity_profile, bet_research, nearest_color), and the Pipeworx brand is used as both prefix and suffix. Readable but inconsistent.
At 34 tools, the surface is far larger than a typical well-scoped server, and the count is especially unjustified for a server named 'Color' where only three tools relate to that name. The breadth stems from bolting a full data-research platform, prediction-market suite, memory store, and subscription system onto what appears to be a simple utility. Too heavy.
For the dominant Pipeworx research domain, the set is unusually thorough: query, grounded verification, deep research, entity resolution, comparisons, claim validation, change feeds, subscriptions, alerts, memory, and discovery are all present. Minor gaps exist (e.g., no direct account management tool, and color coverage only includes convert/contrast/nearest with no palette generation), but these are workaround-able. Completeness is strong for the real domain, if mismatched with the server name.