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 |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds the notion of clearing 'sensitive data' but does not detail behavioral aspects like irreversibility or side effects beyond what annotations already convey.
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, no unnecessary words. Every sentence serves a purpose: defining the tool and providing usage context.
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 tool with destructive and idempotent hints, the description is sufficiently complete. It covers purpose, usage guidelines, and pairing with sibling tools.
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 already describes the parameter. The description adds no additional meaning beyond the schema, meeting baseline expectations.
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) and resource (previously stored memory by key). It distinguishes from siblings 'remember' and 'recall' by mentioning them as pairs, establishing its unique role.
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 three use cases: stale context, task completion, and clearing sensitive data. It does not specify when not to use but provides clear context for appropriate usage.
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 ask_pipeworx family—ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded—plus deep_research all describe the same router under slightly different modes, and the six polymarket tools overlap heavily around edge detection and arbitrage. ai_visibility_check and scan_competitor_ai_presence are also near-duplicates, so agents will frequently have to choose between tools that appear to do the same thing.
All names use snake_case and several families share prefixes (ask_pipeworx, polymarket_, pipeworx_, destatis_), which helps discoverability. However the pattern is not consistent: bare verbs (remember, recall, forget), adjective_noun phrases (recent_alerts, recent_changes), and noun_noun names (entity_profile, bet_research) are all mixed.
With 33 tools, the surface is well past the 25+ threshold and mixes unrelated concerns: Destatis statistics, a general data router, prediction-market analytics, memory, and AI-marketing scans. The count could be justified if split into separate servers, but as one set it feels over-stuffed.
For the broad data-retrieval/research purpose the descriptions reveal, coverage is strong: lookup, grounded answers, validation, entity resolution, comparison, change feeds, subscriptions, memory, and Destatis search/table are all present. The only notable weakness is that the Destatis-specific surface is just search-and-fetch, which is thin for a server literally named Destatis, but this is offset by the general router.