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 readOnlyHint=false. The description adds useful behavioral context about why to delete (stale context, sensitive data), enhancing transparency beyond annotations.
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 wasted words. It front-loads the action and purpose, then provides usage guidelines.
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-by-key tool with no output schema, the description covers the action, when to use, and pairing with siblings. It is complete for the level of complexity.
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 a clear parameter description 'Memory key to delete'. The description adds no new semantic information beyond the 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?
The description uses the strong verb 'Delete' and specifies the resource 'previously stored memory by key'. It also distinguishes from siblings by stating 'Pair with 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?
The description explicitly states when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also mentions pairing with related tools.
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.
Several clusters overlap: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near variants (beta currently identical), and the prediction-market tools share adjacent territory. The descriptions do delineate most use cases, but an agent could easily confuse the ask_pipeworx variants or pick between polymarket_edges and bet_research.
Naming is a mix of domain-prefixed verbs (data360_get_data, pipeworx_feedback), bare verbs (forget, recall, subscribe), and noun phrases (entity_profile, recent_changes, polymarket_edges). The ask_pipeworx family is consistent, but there is no server-wide verb_noun convention and tool names are not predictable from their function.
34 tools is too many for a well-scoped server, and the set spans unrelated areas: data retrieval, prediction markets, memory, subscriptions, npm dependency scanning, and llms.txt generation. While each tool has a purpose, the overall surface feels sprawling rather than focused.
The core data/research workflows are well covered: ask/grounded/deep research, entity identity and profiles, comparisons, claim validation, and subscription lifecycle management are all present. Minor gaps exist, such as no explicit raw-record fetch tool and some auxiliary features appearing as one-off utilities, but no major dead ends are apparent.