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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide destructiveHint=true and idempotentHint=true, so the description's claim of deletion is consistent but adds no new behavioral details, such as handling of non-existent keys or side effects.
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 sentences with zero wasted words. The first sentence states the primary action, and the second provides usage guidance and tool pairing. Perfectly concise.
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 single parameter, full schema coverage, and annotations, the description is mostly complete. It lacks details on return behavior or error handling (e.g., missing key), but that is acceptable for a simple memory deletion tool.
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% and the parameter description 'Memory key to delete' is identical in both schema and description. The description adds no semantic value beyond what the schema already provides.
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 'Delete a previously stored memory by key', which is a specific verb and resource. It also distinguishes from sibling tools by mentioning '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 provides explicit usage scenarios: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also mentions related tools (remember, recall), helping the agent decide when to use this tool.
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 occupy nearly identical roles (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools), and ask_pipeworx_beta is explicitly the same router as ask_pipeworx. Company-data tools (entity_profile, compare_entities, recent_changes, validate_claim) and the Polymarket family also overlap heavily, making selection error-prone despite detailed descriptions.
Tool names are consistently lowercase snake_case with a verb_noun pattern (search_notices, get_notice, find_a_tender_recent, validate_claim). Even longer names like polymarket_edge_tracker and ask_pipeworx_grounded follow a predictable style with no camelCase or mixed conventions.
36 tools is already excessive for a focused server, and the 'Uk Contracts' name covers only five of them (search_notices, recent_notices, get_notice, find_a_tender_recent, find_a_tender_notice). The remaining 31 are unrelated Pipeworx/Polymarket/AI-marketing utilities, so the count badly mismatches the apparent scope.
For UK public procurement, the five relevant tools provide search, recent listing, and full-detail retrieval for both Contracts Finder and Find a Tender Service, covering the core workflows well. Minor gaps include no tender-specific alert/subscription support and no server-side keyword search for the high-value FTS feed.