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, so the description doesn't need to re-state safety. It adds context about clearing sensitive data and when deletion is appropriate. No contradiction, but doesn't describe behavior on non-existent keys, though idempotent hint covers that implicitly.
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, action first, usage guidance second. No redundant wording. Perfectly sized.
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?
Simple 1-param tool with strong annotations (destructive, idempotent) and schema. Description covers purpose and usage. Could mention return value or irreversible nature, but annotations already convey the destructive aspect. Adequate.
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 has 100% coverage with a clear description of 'key' as 'Memory key to delete'. The description's phrase 'by key' adds no additional semantic detail. 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?
Description uses specific verb 'Delete' with resource 'previously stored memory' and identifies key as the identifier. Clearly distinguishes from sibling tools 'remember' and 'recall' by contrasting its function.
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 conditions: stale context, task completion, clearing sensitive data. Mentions pairing with remember and recall, implying alternatives. Lacks explicit exclusion conditions, so not a 5.
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 jobs, but ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research are overlapping query/research entry points—and ask_pipeworx_beta is currently identical to ask_pipeworx. Similarly, ai_visibility_check and scan_competitor_ai_presence overlap by composition. The descriptions are detailed enough to choose correctly with care, but the boundaries are not always crisp.
All names use lowercase snake_case, which keeps the surface readable, but the naming conventions are mixed: some are imperative verbs (get_tle, list_recent, validate_claim), some are noun phrases (entity_profile, recent_alerts, pipeworx_trending), and several use domain prefixes without a clear verb (polymarket_arbitrage, polymarket_edges). This is still discoverable naming, but it does not follow a consistent verb_noun pattern.
34 tools is well beyond the well-scoped range, and the vast majority belong to a broad Pipeworx research/prediction-market platform rather than the server's apparent 'tle' satellite theme. Only get_tle, list_recent, and search_satellites directly match the server name. It feels like several tool surfaces aggregated into one server rather than one coherent product.
For the satellite TLE theme, NORAD lookup, name search, and recent-catalog listing are covered, but orbit propagation, pass prediction, and historical TLE data are missing. For the broader data-research surface, coverage is rich—query, grounded answers, entity resolution, comparison, validation, subscriptions, and memory are all present—so agents have workable paths for most tasks, but the server's mixed scope creates obvious thematic gaps.