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 and idempotentHint, and the description reinforces the destructive nature by saying 'Delete' and 'clear sensitive data.' It adds context about what is destroyed ('previously stored memory') and why (stale or sensitive), though it doesn't disclose edge cases like missing keys. This is consistent with annotations and adds some behavioral context beyond the hints.
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?
Three short sentences: the first states the action, the second specifies when to use it, and the third references sibling tools. Every sentence contains essential information and there is no redundancy or padding.
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?
The tool is a simple single-parameter delete operation with no output schema. The description covers its purpose, use cases, and companion tools, while annotations handle safety/destructive flags. It is fully contextual for the agent to invoke it correctly.
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 already fully describes the 'key' parameter as 'Memory key to delete' (100% coverage). The description repeats 'by key' without adding new syntax, format, or additional parameter details, so it does not exceed the schema's semantic contribution.
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 opens with 'Delete a previously stored memory by key,' which is a specific verb (delete) and resource (memory) that clearly distinguishes the tool from siblings like remember and recall. It unambiguously states the primary function.
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 usage triggers: 'Use when context is stale, the task is done, or you want to clear sensitive data.' It also says 'Pair with remember and recall,' naming companion tools and suggesting alternatives by contrast.
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 are near-duplicates or heavily overlap: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are nearly identical, several polymarket_* tools cover the same edge-detection domain, and scan_competitor_ai_presence is just a wrapper around ai_visibility_check. Agents will frequently struggle to pick the right tool.
Most tools use snake_case, but the pattern is inconsistent: verb_noun (estimate_electricity, resolve_entity), noun_phrase (entity_profile, recent_changes), brand-specific (ask_pipeworx, pipeworx_trending), and family-prefixed (polymarket_*). The naming is readable but lacks a single cohesive convention.
At 34 tools, the set is far larger than the 'Carbon Interface' name implies. It piles together carbon estimation, a massive data-router, prediction-market analysis, memory, subscriptions, and meta-tools, making the surface feel bloated and unfocused.
The carbon-estimation purpose is thin (only three estimators with no lifecycle), but the broader Pipeworx/data and prediction-market subdomains are fairly well covered. Gaps exist in each subdomain (e.g., no order placement for betting, no carbon scope beyond the three estimates), and the lack of a clear primary domain makes coverage hard to assess.