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 about clearing sensitive data and that the memory was saved earlier, which is helpful but not extensive. No contradiction with 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?
Three concise sentences: first states the action, second gives use cases, third relates to siblings. No redundant information, well-structured.
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 simplicity of the tool (delete by key), the description covers purpose, usage scenarios, and relationship to siblings. Annotations cover destructiveness and idempotency. No output schema needed for a delete 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% with a clear description for the key parameter. The description does not add additional meaning beyond what the schema provides, so score is at baseline.
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 tool deletes a previously stored memory by key, specifying the verb ('Delete') and the resource ('memory'). It also mentions pairing with remember and recall, which distinguishes it from siblings that store or 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?
Explicitly provides when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also pairs with remember and recall, giving context about alternative 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 tools form near-overlapping clusters: ask_pipeworx and ask_pipeworx_beta are explicitly identical in behavior, while ask_pipeworx, ask_pipeworx_grounded, and deep_research have overlapping scopes. The five polymarket tools also share a common prediction-market domain and could be confused despite detailed descriptions. Some boundaries between 'meta' tools such as discover_tools, suggest_questions, and ask_pipeworx are also fuzzy.
The majority of tools use lowercase snake_case and many follow a verb_noun pattern (ask_pipexors, search_within, generate_llms_txt, destroy_tools), which is readable. However, there are inconsistent orderings like ai_visibility_check and dk_tender_search, plus several one-word verb tools (remember, forget, recall) alongside noun_verb forms. So the style is mostly regular but does not follow a single consistent pattern.
34 tools is very ot heavy for a general-purpose data platform, but the server name 'Udbud Dk' implies a narrow Danish tender scope. Only 3 of the 34 tools actually concern Danish procurement, while the rest form a broad question-answering, prediction-market, subscription, and memory platform. The count feels bloated and mismatched relative to the apparent server focus.
For the broad data domain, the server covers a wide range: lookup, grounded answers, entity resolution, fact-checking, company profiles, comparisons, change feeds, polymarket opportunities, subscriptions, and memory. But relative to the Danish tender scope implied by the server name, only search/detail/recent exist and missing functionality such as saved searches or notifications for new notices. There are also some odd gaps such as no-direct citation-lookup tool, but the generous question-answering tools compensate.