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 declare destructiveHint=true and idempotentHint=true. The description adds context that this is about 'sensitive data the agent saved earlier' and clarifies the action as deletion, which aligns with destructiveHint. It does not contradict annotations. The description enriches behavioral context by explaining the motivation (clearing stale context or sensitive data), which goes beyond what annotations alone provide.
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 concise sentences front-load the purpose and then provide usage guidelines. Every word adds value; there is no redundancy or filler. Extremely well-structured for an AI agent to parse quickly.
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?
Given the tool's simplicity (one required parameter, no output schema), the description covers all necessary aspects: what it does, when to use it, and how it relates to siblings. No additional context is needed for correct invocation.
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?
Input schema coverage is 100%, with the 'key' parameter fully described ('Memory key to delete'). The description adds no additional information about the parameter beyond what is in the schema. Baseline is 3, and no extra value is provided.
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 a previously stored memory by key'). The verb 'Delete' is specific and directly indicates the resource being acted upon ('memory'). It also implicitly distinguishes itself from sibling tools like 'remember' and 'recall' by mentioning them in a pairing context.
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 provides explicit usage scenarios: 'when context is stale, the task is done, or you want to clear sensitive data'. It also suggests pairing with 'remember' and 'recall', offering guidance on complementary tools. However, it does not explicitly exclude situations where this tool should not be used or suggest direct alternatives beyond the paired tools, which would make it a 5.
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 set contains several clusters of near-overlapping tools: ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, ask_pipeworx/deep_research/validate_claim all handle natural-language queries, and bet_research/polymarket_edges/polymarket_arbitrage scan the same prediction-market space. The descriptions are detailed, but that does not remove the boundary confusion.
Almost all tools use lowercase snake_case with recognizable patterns such as verb_noun or prefix_domain (nihr_, polymarket_, pipeworx_). There are minor deviations like ask_pipeworx_beta vs ask_pipeworx_grounded and mixed noun/verb phrasing, but the naming is predictable overall.
36 tools is beyond the typical well-scoped server size, and the set reads as several products bundled together: NIHR grants, Pipeworx data research, prediction markets, memory, subscriptions, and standalone utilities like generate_llms_txt or scan_dependency. Even for a broad data platform this is too many to navigate coherently, and it is a severe mismatch for a server named 'Nihr'.
Within its subdomains the set covers core workflows: query (ask/deep_research/validate), entity resolution/profile/comparison, NIHR grant lookup by several dimensions, prediction-market analysis through fill-risk, and memory/subscription lifecycles. But it is a collection of partial products rather than one coherent domain, and some outputs such as pipeworx:// citations or detected arbitrage opportunities lack an obvious in-set tool to consume them further.