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 mark destructiveHint=true and idempotentHint=true. Description adds that deletion is for clearing sensitive data, which is consistent and provides additional behavioral context. No contradictions.
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: first states purpose, second provides usage guidance and sibling pairing. No filler, each sentence adds value. 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?
Tool is simple with one param, no output schema, and annotations present. Description covers purpose, when to use, and alternatives (siblings). All necessary information is provided concisely.
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 for the single parameter 'key' with description 'Memory key to delete'. Tool description does not add additional parameter semantics beyond stating 'by key'. Baseline 3 is appropriate as schema carries the burden.
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 clearly states 'Delete a previously stored memory by key', specifying the action (delete), resource (memory), and identifier (key). It distinguishes from siblings by mentioning 'pair with remember and recall', implying different operations.
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: 'context is stale, task done, or clear sensitive data'. It also advises pairing with 'remember and recall', providing context for tool selection. Lacks explicit when-not scenarios but is sufficiently clear.
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.
Multiple tools have unclear boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route to the same 5,714-tool catalog with heavily overlapping purposes, and ask_pipeworx_beta is currently identical to ask_pipeworx. Similarly, bet_research, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, and polymarket_fill_risk all target prediction-market analysis and could easily be confused by an agent. The two FAA tools (faa_regulation, faa_search) are distinct, but they are buried among a dozen unrelated data-lookup and memory tools.
Most tools follow a consistent lowercase snake_case verb_noun or noun_verb pattern (faa_search, resolve_entity, compare_entities, validate_claim, discover_tools, unsubscribe). Minor deviations exist, such as ask_pipeworx and pipeworx_feedback lacking underscores, and the polymarket_* family mixes noun-led names, but overall the naming is readable and predictable.
33 tools for a server named 'Faa Regulations' is a severe mismatch: only 2 of the 33 tools (faa_regulation, faa_search) relate to FAA regulations, with the rest covering general data lookups, prediction markets, SEC filings, memory storage, npm dependency checking, and llms.txt generation. The count is far too high for the stated domain, and most tools do not belong in this server at all.
The actual FAA surface is thin: faa_search provides keyword lookup and faa_regulation returns full text or a part's section list, so basic citation-lookup workflows work, but there is no update/amendment tracking, no browse-by-part navigation beyond a section list, and no related aviation data such as NOTAMs or TFRs. The dominant Pipeworx tool family is unrelated to FAA regulations, so an agent using this server for its apparent purpose would hit dead ends quickly.