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 useful. No contradiction. Lacks mention of irreversibility or confirmation prompts but sufficient for a simple delete.
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 efficient sentences front-loaded with purpose and usage. No wasted words. Every sentence adds value.
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?
Tool has one required param, no output schema, and simple behavior. Description covers purpose, usage context, and relationships with siblings. Fully adequate.
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 param 'key' is described as 'Memory key to delete' in both schema and description. Description adds no extra meaning beyond schema, so baseline 3 applies.
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 clearly states 'Delete a previously stored memory by key', specifying verb (Delete) and resource (memory by key). It distinguishes itself 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?
Explicitly states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also advises pairing with 'remember' and 'recall', guiding against alternatives.
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 in purpose: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, and ask_pipeworx_grounded, deep_research, and validate_claim all query the same underlying data catalog in similar ways. The descriptions provide detailed usage guidance, but the query family and the five-strong Polymarket family still create real misselection risk. Memory, subscription, and FCC tools are clearly distinct.
Tool names are consistently snake_case and mostly follow recognizable verb_noun or prefixed-family patterns (ask_pipeworx_*, polymarket_*, pipeworx_*). The main deviations are bare one-word names like datasets, metadata, query, remember, and forget, plus a few noun-first names like entity_profile and polymarket_arbitrage. Overall the naming is readable and predictable, with only minor inconsistencies.
At 34 tools, this server is well past the 25+ threshold and feels overloaded. It bundles a general-purpose data-query gateway, FCC open-data access, Polymarket analytics, AI-visibility scanning, memory, subscriptions, npm dependency checks, and llms.txt generation into one surface. Each functional area is small on its own, but the combined set would be more coherent split into several focused servers.
The core data lifecycle is well covered: discovery (suggest_questions, discover_tools), single queries (ask_pipeworx), grounded/evidence-backed answers, deep multi-source research, entity resolution/profiling/comparison, change feeds, and fact-checking all exist. FCC open data has search, schema, and query tools, and subscriptions/memory have full CRUD-style coverage. Minor gaps remain (e.g., no direct pipeworx:// URI fetch tool, no enumeration of all discoverable data sources), but they do not block typical workflows.