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 destructive and idempotent behavior. Description adds 'sensitive data' context but lacks details on edge cases like key not found or return value. Acceptable but not exceptional.
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 sentences, front-loaded with purpose, no redundancy. 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?
Complete for a single-parameter destructive tool with good annotations. Includes purpose, usage guidelines, and pairing advice. No output schema needed.
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 covers 100% of parameters with description 'Memory key to delete'. Description adds no new meaning beyond 'by key', so baseline of 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?
Clearly states the tool deletes a memory by key, using specific verb 'delete' and resource 'memory'. Distinguishes from siblings 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?
Provides explicit when-to-use scenarios: stale context, task completion, clearing sensitive data. Names alternatives (remember, recall) and suggests pairing.
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.
Most tools have clearly distinct roles, but there is notable overlap in the ask_pipeworx family (stable, beta, grounded, deep_research), and ask_pipeworx_beta is explicitly described as currently identical to ask_pipeworx. discover_tools and suggest_questions also both serve as meta-guidance, creating some selection ambiguity. The very detailed descriptions help, but they do not fully remove the risk of misselection.
The set mixes verb-first names like compare_entities and validate_claim with noun-first names like entity_profile and polymarket_edges, along with prefix families (polymarket_*, pipeworx_*, ask_pipeworx_*) and bare verbs like forget and search. Everything is snake_case and readable, but there is no single predictable convention across the whole surface.
33 tools for a server labeled 'Jina Reader' is a sprawling surface spanning data routing, prediction markets, memory, subscriptions, and web reading. Even if each tool is individually focused, the count and combined scope feel oversized relative to the server name and the rubric's guidance for well-scoped servers.
Each sub-domain has good lifecycle coverage: memory (remember/recall/forget), subscriptions (subscribe/unsubscribe/list_subscriptions/recent_alerts), entity research (resolve_entity/entity_profile/compare_entities/recent_changes/validate_claim), and Polymarket analysis (edges/arbitrage/fill_risk/kalshi_spread). There are minor gaps like no order execution or simple page summarization, but those appear intentionally out of scope, leaving the surface largely complete.