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 indicate destructiveHint=true and idempotentHint=true. The description adds that deletion is based on a key and hints at privacy ('clear sensitive data'), but does not explain behavior if the key does not exist or confirm idempotent behavior. It adds some value beyond annotations but lacks full behavioral disclosure.
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 comprises only two sentences, each earning its place: the first states the core action and resource, the second provides usage guidance and sibling context. No unnecessary words or repetition.
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 tool with one parameter, no output schema, and annotations covering destructive and idempotent aspects, the description is largely complete. It explains purpose, usage, and relationship to siblings. It could mention success/failure or error handling for missing keys, but the current level is adequate given the tool's simplicity.
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 schema has 100% coverage with a description for the 'key' parameter ('Memory key to delete'). The tool description does not add further meaning or constraints (e.g., format, length, case sensitivity) beyond that. Baseline 3 is appropriate since the schema already describes the parameter adequately.
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 a specific verb ('Delete') and resource ('memory by key'), and explicitly distinguishes from siblings 'remember' and 'recall' by stating the complementary relationship. It also provides usage conditions, making the purpose unambiguous.
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 clearly states when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data.' It also suggests pairing with 'remember' and 'recall'. However, it does not explicitly state when not to use it or list alternatives for similar tasks, though the positive guidance is strong.
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.
Many tools are distinct, but the ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded) heavily overlaps—the beta is explicitly identical to the stable version. The two Chile-specific tools are clear, but the presence of numerous unrelated data tools creates confusion about which tool serves the server's purported purpose.
Naming is inconsistent: some tools follow verb_noun snake_case (chile_get_tender, chile_search_tenders), others use plain verbs (ask_pipeworx) or noun_verb patterns (polymarket_arbitrage, entity_profile). Mixed conventions and varying levels of specificity make the set feel uncoordinated.
33 tools is excessive for a server named 'Chile Procurement'—only two tools relate to Chile procurement, while the rest are generic Pipeworx data utilities. The count is not scoped to the server's stated purpose; it appears to be a bundled general-purpose toolkit rather than a focused procurement interface.
For Chile procurement, only search and get-detail are provided; there is no ability to list all historical tenders, filter by category or amount, or track bidding. The read-only surface covers basic retrieval but lacks common procurement workflows. The broader data tools are complete individually but irrelevant to the server's domain.