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?
The description confirms the destructive nature ('Delete'), which aligns with the annotation 'destructiveHint: true'. It adds context that it operates on 'memory' by 'key', but does not reveal side effects or error behavior. Since annotations already cover safety profile (destructive, idempotent), the description adds moderate value.
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?
The description is three sentences, front-loaded with the purpose, followed by usage context and sibling pairing. No extraneous information; every sentence serves a purpose.
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?
The tool is simple (1 param, no output schema). The description covers purpose, usage, and tool relationships. Missing detail on behavior for non-existent keys, but the idempotent hint implies no error. Overall complete enough for effective use.
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?
The input schema already fully describes the 'key' parameter (100% coverage). The description merely echoes 'by key' without adding new semantic details such as format, constraints, or examples beyond the schema's own example. Baseline 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?
The description clearly states the action ('Delete a previously stored memory by key') and specifies the resource and operation. It distinguishes itself from siblings by explicitly naming 'remember' and 'recall' as complementary tools.
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?
The description provides explicit usage scenarios ('when context is stale, the task is done, or you want to clear sensitive data') and suggests pairing with siblings. It lacks explicit when-not-to-use or alternative recommendations, but for a simple tool it's sufficient.
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 overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded all route questions to similar data sources, while search_within also overlaps with grounded answering. bet_research, polymarket_edge_tracker, and polymarket_fill_risk all target prediction markets. Agents must read descriptions carefully to pick the right variant.
Most tools follow a verb_noun snake_case pattern (ask_pipeworx, bet_research, validate_claim, resolve_entity). Some are single nouns (recent_alerts, recent_changes, key_alerts), a few break the convention (ask_pipeworx_beta, ask_pipeworx_grounded, remember, forget). Overall mostly consistent with minor deviations.
34 tools is a high count for a general-purpose data server, and several seem redundant: ask_pipeworx vs ask_pipeworx_beta vs ask_pipeworx_grounded, polymarket_edge_tracker vs polymarket_arbitrage, and the numerous meta-tools create overhead. A focused dataset server would be better with 10–15 tools.
The surface covers many domains well: SEC filings, economics/FRED, prediction markets, news, clinical trials, San Francisco open data, npm dependencies. Obvious gaps include no financial statement form filings beyond 8-K/10-K, no calendar/event scheduling, and no update-else path for several key objects (but memory tools fill that gap). Attribution currently ships in almost all requested tools, providing evidence.