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 idempotentHint=true. The description adds context about clearing sensitive data and operating on memory, which is consistent and helpful beyond the 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 sentences, no unnecessary words, and front-loads the core action. Every sentence adds value.
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 one-parameter tool with no output schema, the description covers purpose and usage. However, it lacks details on what happens if the key doesn't exist or confirmation of success, which would improve completeness.
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%, so the parameter 'key' is already described. The description only mentions 'by key' and the example provides a sample, adding minimal extra 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,' which is a specific verb and resource. It distinguishes from sibling tools 'remember' and 'recall' by focusing on deletion.
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 provides explicit when-to-use scenarios: stale context, task done, clearing sensitive data. It also suggests pairing with remember and recall, giving context for usage but not explicitly when not to use.
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 overlap heavily: ask_pipeworx_beta deliberately matches ask_pipeworx exactly right now, discover_tools and suggest_questions both serve as what-can-I-do entry points, and ai_visibility_check is just the single-entity version of scan_competitor_ai_presence. An agent will struggle to pick the right variant without carefully reading long descriptions.
All tools are snake_case and several families share clear prefixes (dart_*, polymarket_*, ask_pipeworx_*), but the overall set mixes verb_noun (discover_tools, validate_claim), noun_phrase (entity_profile, deep_research), bare verbs (remember, recall, forget), and prefix-noun (dart_financials). Readable but not unified.
36 tools is far above the 25+ heavy threshold, and the count is inflated by redundancy: ask_pipeworx_beta is a literal duplicate today, suggest_questions overlaps discover_tools, and ai_visibility_check is subsumed by scan_competitor_ai_presence. The broad Pipeworx platform justifies many tools, but the exposed surface is bloated.
The surface covers the apparent domain well: universal querying (ask_pipeworx family + deep_research), tool discovery, entity resolution, profiles, comparisons, change feeds, claim verification, Korean DART filings, Polymarket analysis/fill-risk, memory, subscriptions, and feedback. Minor gaps remain—there's no explicit fetch-by-citation-URI tool despite claims those URIs are fetchable, and no way to retrieve full DART filing text beyond discovery.