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 context about clearing sensitive data, which is beyond annotations. However, it doesn't specify behavior when key is missing, but the idempotent hint implies safe repeated deletion.
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 with the action stated first. It includes purpose, use cases, and pairing, all in concise language with no wasted words.
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?
Given the simplicity of the tool (one parameter, no output schema), the description covers purpose, usage, and context within the sibling tools. It lacks return value specification but the destructive annotation and idempotent hint provide sufficient guidance.
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 input schema has 100% coverage with a description of the 'key' parameter as 'Memory key to delete'. The description simply repeats 'by key' without adding new meaning or examples, so baseline score of 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 explicitly states 'Delete a previously stored memory by key', which is a specific verb+resource. It also distinguishes from siblings 'remember' and 'recall' by its action.
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 specific scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. It also mentions pairing with remember and recall, guiding when to use this tool in the context of the memory system.
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 have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical, and the five polymarket_* tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) all target prediction-market opportunities. The memory tools (remember/recall/forget) are distinct, as are subscriptions, but the routing and Polymarket clusters create real misselection risk.
All names are snake_case, but the pattern is mixed: some are verb_noun (ask_pipeworx, compare_entities, discover_tools, resolve_entity), some are noun_verb or adjective_noun (bet_research, entity_profile, pipeworx_trending, recent_changes), and some are bare nouns/verbs (lookup, query, recall, relatedness). The 'polymarket_*' and 'ask_pipeworx*' families are consistent internally, but the overall set lacks a uniform verb-first convention.
With 34 tools, the server is heavily over-scoped for a server named 'Conceptnet' — the vast majority of tools belong to a separate Pipeworx data-access product, not a semantic-network API. While each tool has a use, the count feels bloated and the server name misrepresents the actual surface.
The ConceptNet portion is complete (lookup, query, relatedness cover graph traversal). The Pipeworx portion is also fairly complete: universal router, grounded mode, deep research, entity profiles, comparisons, claim validation, subscription lifecycle, memory, and feedback. Minor gaps exist (e.g., no direct SEC filing fetch without going through ask_pipeworx), but the meta-tools mostly fill them.