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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true. The description adds context about clearing sensitive data but does not detail side effects beyond deletion. No contradiction.
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. First sentence states action and resource; second provides usage guidance.
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?
Given the tool's simplicity (one parameter, annotations present), the description is sufficient. It does not cover return values or error handling, but that is acceptable for a straightforward delete operation.
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 schema already documents 'Memory key to delete'. The description adds no additional parameter meaning beyond what is in the schema.
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 specifies the action 'Delete' and the resource 'memory by key', clearly distinguishing it from siblings '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?
Provides explicit guidance on when to use: when context is stale, task done, or clearing sensitive data. Also suggests pairing with remember and recall.
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 tool families have fuzzy boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route to the same 5,743 tools with only subtle differences in grounding/fan-out, and the six polymarket_* tools overlap heavily in purpose. Even with detailed descriptions, an agent would frequently need to read the full text to pick the right one, and the beta variant is admitted to be currently identical to the stable router.
All tool names use snake_case with clear family prefixes (ask_pipeworx, polymarket_*, h1b_*, pipeworx_*, subscribe/unsubscribe), making the set look organized. The minor inconsistency is that some names start with an imperative verb (ask, compare, validate, scan) while others are bare nouns (entity_profile, deep_research, bet_research), so the verb_noun pattern is not universal.
34 tools is well beyond the recommended range for an MCP server, and many are near-duplicates (three ask_pipeworx variants, six prediction-market analyzers, three memory/three subscription tools). The breadth may reflect a genuinely large data catalog, but exposing it all as top-level MCP tools makes the surface heavy and hard to navigate.
For the actual data-platform scope, coverage is solid: lookups, research, memory, subscriptions, and validation are all present. However, a direct fetch tool for the advertised pipeworx:// citation URIs is missing (deep_research even conditions citations on resources/read existing), and the server's stated H-1B identity is underrepresented with only three specialized tools.