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 declare destructiveHint=true and idempotentHint=true, so the bar is lower. The description adds context that memory was 'saved earlier' and frames deletion as clearing sensitive data, which enriches the safety profile without contradicting 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?
Three purposeful sentences: function, when-to-use, and related tools. No redundant words, and the most important information is front-loaded. Ideal conciseness.
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 single-parameter tool with good annotations, the description covers purpose, usage context, and related tools. It doesn't explain behavior for missing keys, but idempotentHint mitigates that gap. Slight room for more edge-case detail, but otherwise complete.
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 a clear description for the key parameter ('Memory key to delete'). The description's 'by key' adds no new semantic meaning beyond the schema, so 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 opens with a specific verb and resource: 'Delete a previously stored memory by key.' This clearly states what the tool does and distinguishes it from siblings like remember (store) and recall (retrieve).
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?
Explicit usage conditions are provided: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names related tools ('Pair with remember and recall'), giving direct alternative guidance.
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 nearly indistinguishable in role: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are all variants of the same router, with the beta version explicitly noted as currently identical to the stable one. The six Polymarket tools also overlap heavily around edge-finding, arbitrage, and fill-risk analysis, making misselection likely.
Names are uniformly snake_case and groupable into prefixes like polymarket_* and pipeworx_*, but the set does not follow a consistent verb_noun convention. Noun-first names like entity_profile and recent_alerts sit alongside verb-first names like read_feed and validate_claim, and product-name suffixes such as ask_pipeworx_beta/grounded add further inconsistency.
At 34 tools, the surface is well past the 25+ threshold and far broader than the 'Crypto Feeds' name suggests. The set spans feed reading, general data research, prediction markets, AI-brand visibility audits, npm dependency scanning, memory, and subscriptions, making it feel like a platform-wide dump rather than a focused MCP server.
The broad research workflow is well covered with query, grounded answer, deep research, entity profiles, comparisons, fact-checking, and entity resolution. However, feed functionality is read-only with no feed management, subscription types do not include crypto feeds despite the server name, and there is no dedicated tool for resolving the advertised pipeworx:// citation URIs.