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?
The annotations already declare destructiveHint=true and idempotentHint=true, so the agent knows this is a destructive, idempotent operation. The description adds that it clears 'sensitive data' and that the memory was 'previously stored,' but this is more about purpose than behavioral detail. It does not contradict the annotations, but it also does not significantly extend beyond them.
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 exactly two sentences: the first states the core action, the second gives usage guidance and references related tools. Every word earns its place, with no filler or redundancy.
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 tool with one required parameter, a complete schema, and annotations covering destructiveness and idempotency, the description sufficiently explains purpose and usage. It does not mention error handling (e.g., what happens if the key doesn't exist), but that is arguably covered by the idempotentHint annotation and is not essential for this simple operation.
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%: the 'key' parameter is described as 'Memory key to delete.' The description's mention of 'by key' adds no new meaning beyond the schema, so it earns the baseline score for high coverage.
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 clearly specifies the action (delete) and the resource (memory by key). It also mentions pairings with 'remember' and 'recall,' which helps distinguish it from the sibling tools that store and retrieve memories.
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'), and it names the related tools 'remember' and 'recall' for context. However, it lacks an explicit 'when not to use' statement, which prevents a perfect score.
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 tools form overlapping families (ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded/deep_research, plus the six polymarket_* tools), and ask_pipeworx_beta is currently an exact behavioral duplicate. The long descriptions usually disambiguate them, but an agent could still struggle to quickly choose between similar research and edge-detection tools.
Names are uniformly snake_case and prefix families like pipeworx_* and polymarket_* help, but there is no consistent verb_noun pattern: subjects, table_meta, recent_alerts, and entity_profile are noun phrases while remember, generate_llms_txt, and compare_entities are action-first. The mixed conventions are readable but less predictable than a uniform pattern.
34 tools is well into the 'too many' range for a single tool set, even if each is individually documented. Several could plausibly be consolidated, such as ask_pipeworx_beta, the polymarket edge tools, and the AI-visibility pair.
For its broad stated purpose, the set covers the full lifecycle: lookup/research, entity profiles, comparisons, claim validation, prediction-market edge analysis, memory, subscriptions, and discovery. Minor gaps exist, such as no direct fetch-by-URI tool or subscription update path, but most workflows have a clear route.