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 indicate destructiveHint=true and idempotentHint=true, so the description's addition of 'clear sensitive data' and 'stale context' provides useful behavioral context beyond the technical hints. No contradictions found.
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 with no wasted words. The main action is front-loaded in the first sentence, usage guidance in the second, and a brief reference to related tools. Every sentence earns its place.
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 tool with one parameter, no output schema, and well-covered annotations, the description fully covers purpose, usage, and relationships. No gaps remain.
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?
Input schema has 100% coverage for the single parameter 'key' with description 'Memory key to delete'. The tool description does not add additional parameter semantics beyond what the schema already provides, meeting the baseline for high schema coverage.
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?
Description clearly specifies the verb 'Delete', the resource 'previously stored memory', and the method 'by key'. It leaves no ambiguity about the tool's function and distinguishes it from siblings by explicitly mentioning pairing with 'remember' and 'recall'.
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?
Provides explicit guidance on when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data'. Also implies when not to use by pointing to alternative tools ('remember' and 'recall'), offering clear context for decision-making.
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 have unclear boundaries: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, while ask_pipeworx, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all overlap in the 'how should I query data' space. Additionally, the tool set mixes two unrelated domains (Zenodo and Pipeworx) without any organizing principle, forcing agents to guess which family applies.
All names are lowercase snake_case, but the semantic patterns are inconsistent: bare nouns for Zenodo tools (search, record, communities), product-prefixed names (pipeworx_*, polymarket_*), generic verbs (remember, forget, recall), and verb_noun compounds (list_subscriptions, generate_llms_txt). The server is named Zenodo, yet most tools carry a pipeworx or polymarket prefix, making the naming feel arbitrary relative to the server's identity.
36 tools is excessive for a server whose stated identity is Zenodo; only 5 of the 36 tools actually relate to Zenodo, with the remaining 31 belonging to a separate Pipeworx data platform. This suggests a bundled or mislabeled server rather than a deliberately scoped tool surface, and even the Zenodo subset alone would be thin.
For the Zenodo domain implied by the server name, the surface is severely incomplete: it covers search and read/retrieval (search, record, record_files, communities, community_records) but entirely omits the deposit workflow that is central to Zenodo — no create, update, delete, versioning, or file upload/download tools. The unrelated Pipeworx side is over-built, but the actual Zenodo use case leaves agents with dead ends.