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 provide destructiveHint=true and idempotentHint=true, so the description carries less burden. It adds behavioral context about when to use but does not elaborate on the deletion behavior beyond what annotations imply. No 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, no redundant information. Every word adds value.
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 single-parameter destructive tool with annotations, the description is complete. It explains the operation, when to use it, and how it relates to sibling tools, leaving no obvious gaps.
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 descriptions cover 100% of the single parameter 'key', so the description adds no additional semantic value beyond stating 'delete by key'.
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) and resource (memory by key). It distinguishes from siblings by mentioning pairing with 'remember' and 'recall', which are listed as sibling 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?
Provides explicit usage contexts: stale context, task completed, clearing sensitive data. Also notes pairing with related tools, offering guidance on when to use this tool versus alternatives.
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 have overlapping purposes, e.g., multiple ask/tools for querying (ask_pipeworx, ask_pipeworx_grounded, deep_research) and multiple company analysis tools (entity_profile, compare_entities, recent_changes). The prediction market tools (bet_research, polymarket_arbitrage, etc.) further blur distinctions. Agents would frequently select the wrong tool.
Naming conventions are inconsistent: snake_case (ask_pipeworx, dataset_info), camelCase (ai_visibility_check, scan_competitor_ai_presence), and phrases (pipeworx_feedback, polymarket_arbitrage). No pattern emerges, making tool discovery harder.
33 tools is excessive for a server ostensibly about Île-de-France Open Data. Only 3 tools (dataset_info, query, search_datasets) relate to that domain, while the rest are a general-purpose data agent with many disjoint capabilities. The count feels bloated and unfocused.
For the declared purpose (Île-de-France data), the tool set is missing CRUD operations (no create/update/delete). For the actual general data use, there are gaps like missing person entity resolution, data visualization, and file handling. The deep_research tool requires an account, creating a barrier.