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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, so the description's 'delete' aligns with those. It adds the context of clearing sensitive data, which gives a rationale for the destructive action, but does not disclose additional behavioral details like what happens if the key does not exist or whether deletion is reversible.
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 that front-load the core action ('Delete a previously stored memory by key') and then provides usage context. Every word earns its place, with no redundancy or 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 one-parameter tool with comprehensive annotations (destructive, idempotent) and no output schema, the description covers purpose, usage timing, and relationships to sibling tools. It is complete for the tool's complexity.
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 schema already describes the parameter as 'Memory key to delete' with 100% coverage. The description adds only 'by key' and 'previously stored memory,' which does not significantly enhance the schema's meaning. Baseline 3 is appropriate because the schema does the heavy lifting.
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 tool's function: 'Delete a previously stored memory by key.' This uses a specific verb (delete) and resource (memory), and explicitly distinguishes it from the sibling tools 'remember' and 'recall' by positioning it as the deletion counterpart.
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 usage scenarios: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also mentions pairing with 'remember and recall,' giving clear contextual guidance without needing to explicitly exclude alternatives.
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 tool groups overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer questions against the same data sources, and the Polymarket suite (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, bet_research) has unclear boundaries. An agent would struggle to pick the right one.
Names mix verb phrases (search_pubmed, get_abstract, validate_claim) with noun phrases (entity_profile, polymarket_arbitrage, bet_research) and bare verbs (remember, forget). The ask_pipeworx family uses a non-standard prefix, and there's no consistent verb_noun pattern across the set.
37 tools is far too many for a server that presents as a PubMed tool. The majority are unrelated to biomedical literature (memory, subscriptions, prediction markets, real estate, etc.), making the surface feel bloated and unfocused.
The PubMed-specific tools form a complete lifecycle: search, citation metadata, abstract, full text, forward citations, and related articles. However, the server's broader domain is unclear and unevenly covered — many non-PubMed areas have partial coverage.