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?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the basic behavioral profile is known. The description adds contextual use cases (clearing sensitive data) but no additional behavioral traits such as irreversibility or side effects beyond what annotations imply. This is consistent with annotations.
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 with no fluff. The action is front-loaded, the use cases are efficiently listed, and the sibling pairing adds useful context in a compact way.
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 and no output schema, the description covers purpose, usage, and relation to siblings. It could add a note about irrevocability, but that's already implied by destructiveHint, so this is complete enough.
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 has 100% coverage: the 'key' parameter is described as 'Memory key to delete'. The description's 'by key' merely repeats what the schema already provides, so it adds no new semantic meaning. 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 starts with a specific verb ('Delete') and resource ('previously stored memory by key'), making the tool's function immediately clear. It also distinguishes itself from sibling tools by noting it pairs with 'remember and recall', which clarifies its role in the memory workflow.
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 gives explicit when-to-use guidance: 'context is stale', 'task is done', or 'clear sensitive data'. It mentions pairing with sibling tools but doesn't explicitly state when not to use it or name direct alternatives, so it falls just short of 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.
Many tools overlap or are near-duplicates: ask_pipeworx and ask_pipeworx_beta are currently identical, and there are multiple prediction-market tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) with fine-grained but confusing distinctions. The mix of Bitfinex market data tools with an unrelated Pipeworx research suite makes tool selection genuinely ambiguous.
All names use lowercase snake_case, but the semantic pattern is inconsistent: bare nouns (ticker, candles, trades, stats), verb_noun phrases (validate_claim, compare_entities, generate_llms_txt), and large prefixed families (ask_pipeworx*, polymarket_*) coexist. This mixed convention gives no reliable cue to a tool's function.
42 tools is excessive for a server named 'Bitfinex'. Only about a dozen tools actually relate to the crypto exchange (ticker, candles, trades, book, liquidations, etc.); the rest are a grab bag of Pipeworx research, prediction markets, memory, and subscription features. The count bloats the surface and obscures the server's purpose.
The set has no coherent scope. For a Bitfinex server, there are no account/trading tools, only market data. For the buried Pipeworx functionality, the surface is extensive but unrelated to Bitfinex. The overall result is an incomplete hodgepodge with no clear lifecycle or workflow for a single domain.