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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description's 'Delete' aligns with the annotations' destructiveHint=true and idempotentHint=true. It goes slightly beyond annotations by mentioning clearing sensitive data and pairing with related tools, but it does not add details about irreversibility, failure modes, or permissions. Since annotations already cover the core safety profile, a score of 3 is appropriate.
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 two sentences with no redundant words. The first sentence states the action and target; the second provides when-to-use and related tools. Every sentence adds value, making it appropriately 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?
For a one-parameter destructive tool with rich annotations, the description covers purpose, usage, and related tools. It does not mention what happens after deletion (e.g., success message or error for missing key), but given the tool's simplicity and the lack of an output schema, this is a minor gap. Overall it is well-rounded.
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 description coverage is 100% for the single 'key' parameter, so the baseline is 3. The description only says 'by key', which adds no new meaning beyond the schema's 'Memory key to delete'. No extra syntax, formatting, or examples are provided beyond 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 uses the specific verb 'Delete' with the resource 'a previously stored memory' and specifies the mechanism 'by key'. This clearly distinguishes it from sibling tools like recall and remember, which retrieve or store memories.
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?
It provides explicit use cases ('when context is stale, the task is done, or you want to clear sensitive data') and suggests pairing with remember and recall. It lacks an explicit 'do not use when' statement, but the guidance is clear enough for most scenarios.
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 heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates, while deep_research, validate_claim, and bet_research blur the same routing/grounding line. The polymarket_* family also has five tools covering edges, arbitrage, fill risk, and edge decay with significant functional overlap, making misselection likely despite very detailed descriptions.
Naming mixes verb_noun tools (get_pair, compare_entities, suggest_questions) with noun-style tools (entity_profile, recent_changes, bet_research) and bare verbs (remember, recall, forget). The polymarket_ and pipeworx_ prefixes add some structure, but overall the naming is inconsistent and doesn't follow a predictable pattern.
The server is named 'exchangerate' but exposes 33 tools, only two of which (get_pair, get_rates) relate to exchange rates. Even as a general data platform 33 tools is at the extreme high end, and for the stated server purpose the count is wildly inappropriate.
For an exchange-rate server, the surface is severely incomplete: there is no historical rate lookup, no amount conversion, no supported-currency listing, and no rate-change monitoring. The actual tool content covers a broad research platform, but that is entirely mismatched with the server name, leaving the implied exchange-rate domain almost completely uncovered.