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 agent knows the operation is destructive and safe to repeat. The description adds context beyond annotations by explaining why deletion is appropriate (stale, done, sensitive data) and that it removes data saved earlier. It does not contradict 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?
Two sentences, front-loaded with the core action, and every clause adds value: the action, the conditions for use, and the pairing with related tools. No filler or repetition.
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 annotations covering safety and idempotence, the description fully covers purpose, usage, and relationships. No output schema exists, but none is needed for a deletion action. The tool is contextually 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%; the 'key' parameter is documented as 'Memory key to delete'. The description repeats 'by key' without adding new semantics. Baseline of 3 is appropriate when the schema fully documents the parameter.
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 uses a specific verb ('Delete') and resource ('previously stored memory') and clearly identifies the action by key. It distinguishes from siblings like remember (store) and recall (retrieve), making the tool's purpose unambiguous.
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 when-to-use guidance is provided: 'Use when context is stale, the task is done, or you want to clear sensitive data.' It also suggests pairing with remember and recall, indicating relationship to sibling tools. No alternative tools are named for exclusion, but the guidance is concrete and actionable.
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.
ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded form a confusing cluster—beta currently behaves identically to the stable router. The six polymarket_* tools also share overlapping boundaries (edges vs. arbitrage vs. research vs. fill risk), requiring deep reading to select correctly.
There are some coherent families (ask_pipeworx_*, polymarket_*, subscribe/unsubscribe/list_subscriptions, remember/recall/forget), but the overall style is mixed: verb-first names like compare_entities sit next to noun-first names like entity_profile and recent_changes. Everything is snake_case, so it is readable, just not driven by a single consistent convention.
31 tools is too many for a single MCP surface, and each carries a very dense description. The server is essentially several different products bundled together: data access, deep research, prediction markets, AI visibility, memory, subscriptions, and utilities.
The data/research workflows are deeply covered: simple queries, grounded answers, deep research, entity resolution, comparisons, company profiles, recent changes, claim validation, and discovery. Minor gaps exist—no actual order placement for prediction-market trades, no subscription editing, and limited full-catalog browsing for the 5,596 underlying tools.