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 readOnlyHint: false, so the description carries a lower burden. It adds context about deleting previously stored memory and clearing sensitive data, but these are use-case clarifications rather than deeper behavioral disclosures (e.g., irreversibility, confirmation steps). No contradiction exists, but the added value is modest.
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, front-loaded with the primary action, and contains no filler. Every sentence earns its place: the first states purpose, the second provides usage context and related tools.
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 one-parameter, non-output-schema tool with annotations covering destructive behavior, the description is sufficiently complete. It explains what the tool does, when to use it, and how it relates to siblings. No major gaps remain for an agent to invoke it correctly.
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 description coverage is 100% — the only parameter 'key' is described as 'Memory key to delete.' The tool description adds no further semantic nuance beyond restating the key concept, so the schema adequately handles parameter explanation. Baseline 3 is appropriate.
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 states a specific verb and resource: 'Delete a previously stored memory by key.' This clearly distinguishes the tool from siblings like 'remember' (store) and 'recall' (retrieve), leaving no ambiguity about its function.
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 conditions for use ('when context is stale, the task is done, or you want to clear sensitive data') and names related tools ('Pair with remember and recall'). It lacks a direct 'when not to use' clause, so it doesn't fully meet the 5-level criteria, but the guidance is clear and actionable.
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 overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all serve queries, with ask_pipeworx_beta explicitly identical to ask_pipeworx. Prediction-market tools (polymarket_edges, polymarket_arbitrage, polymarket_fill_risk, bet_research, etc.) also have unclear boundaries, making tool selection tricky for an agent.
Tool names are consistently lowercase snake_case with a mostly verb-first pattern (get_work, search_works, list_subscriptions, validate_claim). Minor deviations exist: some names are noun-first (entity_profile, recent_changes) and prefixes vary (get/search/list/ask/scan), but the overall convention is predictable and readable.
34 tools is far too many for a server named 'crossref', and only three tools actually relate to Crossref. The rest form a sprawling utility belt covering data routing, memory, subscriptions, prediction markets, AI visibility, and npm scanning — a scope mismatch that makes the server feel like a kitchen sink rather than a focused offering.
The Crossref-specific surface is thin: search_works, get_work, and get_journal cover discovery and metadata but lack citation lookup, author search, and funder information. The broader Pipeworx surface is extensive but has no unifying domain, so it's impossible to consider the overall toolset complete for any coherent purpose.