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 safety profile is covered. The description adds value by explaining the rationale for deletion (stale context, task completion, sensitive data), which is useful behavioral context 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?
The description is three sentences with no wasted words: a clear action statement, a usage condition, and a sibling pairing hint. It is front-loaded and every sentence contributes to understanding.
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 annotations covering destructive behavior and a fully documented schema, the description fully covers when and why to use it. No output schema exists, and the description is complete for the tool's simplicity.
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% with the key parameter described as 'Memory key to delete.' The description only repeats 'by key' without adding extra meaning, so it does not significantly enhance the schema's parameter documentation.
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 uses a specific verb ('Delete') and a clear resource ('previously stored memory by key'), which precisely states the tool's function. It also distinguishes the tool from its siblings by focusing on memory deletion rather than recall or storage.
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 states when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also hints at complementary tools by saying 'Pair with remember and recall,' providing contextual direction.
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 effectively indistinguishable or near-duplicates: ask_pipeworx_beta is explicitly an identical copy of ask_pipeworx with no active experimental changes, and ask_pipeworx_grounded is a variant of the same router. discover_tools, suggest_questions, deep_research, and the ask_pipeworx family also heavily overlap as discovery/answer surfaces, while bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_fill_risk create a dense prediction-market cluster with fuzzy boundaries.
Everything is snake_case and many names follow a readable verb_noun pattern (search_works, resolve_entity, validate_claim, suggest_questions), but conventions are mixed: noun-first domain-prefixed names (polymarket_edges, pipeworx_feedback, pipeworx_trending), bare verbs (remember, forget, recall), and adjective_noun names (deep_research, recent_changes) coexist. The inconsistency is not chaotic, but it is not a unified scheme.
36 tools is well over the 25-tool threshold for a heavy toolset, and the count is inflated by many tangential concerns: memory, subscriptions, feedback, trending, npm dependency scanning, AI visibility, and llms.txt generation. Only a small subset actually serves the stated OpenAlex/scholarly purpose, so the size feels bloated rather than well-scoped.
For a server named openalex, the scholarly surface is incomplete: works support search and fetch, but authors and institutions only support search with no get-by-ID, concepts support get but no search, and major OpenAlex resource types like sources, publishers, funders, and topics are absent. The many non-OpenAlex tools do not fill these gaps and instead dilute the domain coverage.