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 indicate destructiveHint=true, but the description adds context about clearing stale/sensitive data, providing value beyond annotations without contradiction.
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, front-loaded with the core action, and no wasted words. Every sentence earns its place.
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 delete tool with one parameter, complete annotations, and no output schema, the description fully covers purpose, usage, and safety context.
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 coverage is 100%, and the description does not add additional parameter details beyond what the schema already provides.
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 states 'Delete a previously stored memory by key' with a specific verb and resource, and distinguishes from siblings like 'remember' and 'recall'.
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 is done, clear sensitive data') and mentions pairing with sibling tools 'remember' and 'recall'.
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.
The server mixes three near-identical ask_pipeworx variants (stable, beta, grounded) where beta is currently described as functionally identical to stable, plus several overlapping discovery and research tools (discover_tools, suggest_questions, deep_research, validate_claim, ask_pipeworx). Multiple entity/comparison/change tools (entity_profile, compare_entities, recent_changes) and several Polymarket tools further blur boundaries, requiring careful reading of long descriptions to pick correctly.
Many tools follow a clear verb_noun snake_case pattern (list_dataflows, get_data, compare_entities, validate_claim, resolve_entity), and the polymarket_* prefix groups the prediction-market family consistently. However, naming is mixed: bare verbs (remember, forget, recall), noun phrases (dataflow_structure, entity_profile), brand-prefixed tools (pipeworx_feedback, pipeworx_trending), and inconsistent verb choices like ask_pipeworx vs ask_pipeworx_grounded vs suggest_questions.
34 tools is heavy for a server named Ilostat, especially since only three tools (list_dataflows, dataflow_structure, get_data) actually serve ILOSTAT data. The rest form a broad general-purpose data/prediction-market platform that appears bolted on rather than scoped to the server's stated identity.
For the ILOSTAT domain specifically, the read-only lifecycle is complete: list_dataflows discovers datasets, dataflow_structure explains dimensions/codes, and get_data retrieves observations — no obvious dead ends for public data access. Other embedded subsystems (memory, subscriptions) also have full CRUD, though the overall server lacks a coherent single-domain surface to judge against.