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. Description confirms deletion but adds no extra behavioral context (e.g., behavior on missing key). No contradiction with 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, no wasted words. Purpose and usage are front-loaded. Highly efficient.
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 deletion tool with one parameter and no output schema, the description covers purpose and usage guidelines. Annotations provide destructive/idempotent info. Could mention success/failure behavior but not essential.
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 description 'Memory key to delete'. Main description adds no additional parameter meaning beyond what schema already provides. 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?
Clearly states the tool deletes a previously stored memory by key, using specific verb 'Delete' and resource 'memory'. Distinguishes from sibling tools like 'remember' and 'recall'.
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 (stale context, task done, clear sensitive data) and pairs with related tools (remember, recall). Provides clear guidance on alternative tools.
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 clusters overlap in purpose: ask_pipeworx / ask_pipeworx_beta / ask_pipeworx_grounded / deep_research all answer factual questions, and the six Polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread, bet_research) have subtle boundaries even with detailed descriptions. The descriptions are strong, but an agent must read carefully to reliably pick the right tool.
Most tools follow a verb_noun snake_case pattern (ask_pipeworx, compare_entities, resolve_entity, validate_claim) with recognizable family prefixes (polymarket_*, pipeworx_*, ask_pipeworx_*). Minor deviations like single-noun names (datasets, metadata, query) and mixed lookup verbs (ask vs query vs search vs discover) keep it from a 5.
34 tools is heavy for a single server, and the scope sprawls across general data routing, prediction-market analytics, memory management, subscription bookkeeping, AI visibility checks, and npm dependency scanning. The families are organized, but the count exceeds the 25-tool threshold and would be better split into focused servers.
For a data-research server, coverage is broad: universal routing, grounded answers, deep research, entity profiles, comparisons, change feeds, claim verification, dataset search/query/metadata, subscriptions, and memory. Minor gaps exist—no subscription update operation and no full-catalog browse beyond search—but agents can work around them.