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?
Description confirms destructive nature (delete) consistent with annotations (destructiveHint: true, idempotentHint: true). Adds behavioral context for use cases but lacks details on error handling or success confirmation.
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 the action front-loaded. No wasted words.
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?
Simple destructive tool with no output schema; description doesn't explain return value or error behavior. Adequate but could mention what happens after deletion.
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% with one parameter 'key' described as 'Memory key to delete'. Description adds no additional meaning beyond schema, so 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?
Description clearly states 'Delete a previously stored memory by key' with specific verb 'delete' and resource 'memory'. It distinguishes from siblings by naming '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 (stale context, task done, clear sensitive data) and pairs with remember/recall, providing clear context and 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.
Most tools have clearly distinct purposes, especially the specialized ones like nass_crop_progress and bet_research. However, there is potential confusion between ask_pipeworx, ask_pipeworx_grounded, deep_research, and bet_research, as they all involve querying structured data. The descriptions do attempt to differentiate them, but the overlap could still cause misselection.
Tool names consistently use lowercase with underscores and follow patterns like descriptive prefixes (nass_, pipeworx_, polymarket_) and action verbs (generate_, resolve_, validate_). Minor inconsistencies exist, such as 'search_within' versus 'discover_tools', but overall the naming is predictable and clear.
With 36 tools, the server is on the heavier side but still fits within a reasonable range for a comprehensive data platform. The tools cover a wide variety of domains (agriculture, finance, prediction markets, memory, etc.), and each tool appears to add value. However, the count is borderline high, and some tools like ask_pipeworx could potentially replace many specialized ones.
The tool surface is comprehensive for its purpose: answering questions over structured data with support for analysis, comparison, monitoring, and feedback. There are minor gaps, such as the lack of a direct update mechanism for subscriptions beyond canceling, but the core CRUD operations are covered. The inclusion of meta-tools like ask_pipeworx and deep_research fills many potential gaps.