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 aligns with these by stating 'Delete'. It adds context about clearing 'sensitive data' and that the memory was 'stored earlier', but does not disclose additional behaviors beyond what annotations cover.
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, front-loaded with the action. The first sentence states purpose, the second provides usage context and pairing. Every sentence adds value with no waste.
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 annotations covering destructiveness and idempotency, the description adequately covers purpose, when to use, and parameter. It does not explain behavior on missing keys, but the idempotent hint implies no error. Overall sufficient 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?
Schema coverage is 100% and the schema describes 'key' as 'Memory key to delete'. The description merely says 'by key' without adding new meaning or format details beyond the schema, so it meets the baseline for high 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?
Clearly states 'Delete a previously stored memory by key' with specific verb and resource. Distinguishes from siblings 'remember' and 'recall' by explicitly mentioning them as paired tools, indicating this tool is for deletion.
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 when-to-use scenarios: 'context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing with 'remember and recall', offering clear context for usage. Does not explicitly state when not to use but the positive guidance is sufficient.
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.
Tools cluster into overlapping groups: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates distinguished only by mode; bet_research, polymarket_edges, and polymarket_arbitrage all target prediction-market opportunities. The five OpenSea read tools are distinct, but they are buried among several unrelated domains, making misselection likely.
Names are overwhelmingly snake_case with a verb_noun structure (get_collection, list_owned_nfts, validate_claim, create nothing but still remember/unsubscribe). Pipelined families like ask_pipeworx_* and polymarket_* are consistent, with only minor deviations such as pipworx_trending or bet_research not following a clear verb-object pattern.
36 tools is too many for a coherent server, and the count is inflated by at least four unrelated domains: OpenSea NFT reads, Pipeworx data lookup/research, Polymarket betting, and memory/subscription utilities. Only five tools actually relate to the server's stated OpenSea purpose, so the surface is heavily bloated with off-scope functionality.
The OpenSea-relevant tools cover basic read operations—collections, stats, single NFT, collection NFTs, and owned NFTs—but omit search, events, offers/listings, order book data, and account/contract details. The many unrelated Pipeworx tools do not fill these gaps, so an agent needing real marketplace behavior would hit dead ends.