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 bar is lower. Description adds context about clearing sensitive saved data but doesn't disclose additional side effects like irreversibility or permissions, which would be useful.
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 concise sentences, front-loaded with the action, no filler. 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?
For a simple one-parameter destructive tool with good annotations, the description fully specifies purpose, usage, and related tools. 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 the single 'key' parameter with 100% description, so baseline 3 applies. Description doesn't add syntax or format details beyond the schema, which is sufficient for a simple string key.
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?
Description uses specific verb 'delete' with resource 'memory' and key mechanism, clearly differentiating from sibling tools like remember and recall. It states exact scope and operation.
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 use cases ('context is stale, task done, clear sensitive data') and recommends pairing with remember and recall, but lacks an explicit 'when not to use' clause.
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 have heavily overlapping purposes: ask_pipeworx and ask_pipeworx_beta are currently identical, ask_pipeworx_grounded and validate_claim both perform claim verification, and polymarket_edges and polymarket_arbitrage both surface trading opportunities. While descriptions are detailed, the boundaries are fuzzy and agents could easily select the wrong tool.
Naming mixes verb-first (search, subscribe, recall, validate_claim) with noun-first (dataset, facets, recent, entity_profile) conventions, and some names are just adjectives or nouns. Consistent prefixed groups exist (polymarket_*, ask_pipeworx_*), but the overall style is inconsistent and the server name 'Pangaea' doesn't align with the dominant 'pipeworx' prefix.
36 tools is excessive for a coherent set, especially given the server bundles unrelated domains (earth science, general data research, prediction markets, memory, utilities). Several tools are redundant (e.g., ask_pipeworx_beta duplicates ask_pipeworx), and many are niche (ai_visibility_check, generate_llms_txt, scan_dependency) that don't fit the apparent primary purpose.
The PANGAEA dataset surface covers search, retrieval by ID/DOI, recent, and facets, but lacks export or citation tools. The Pipeworx research tools are broad, but prediction market access has no simple market-price query (only analysis-oriented tools), and there are notable gaps in lifecycle coverage for some subdomains.