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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses deletion behavior beyond annotations by explaining it clears sensitive data. Annotations already indicate destructiveHint=true, so description adds value with usage context.
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, front-loaded with action, efficient and no wasted words.
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?
Comprehensive for a simple tool: explains action, when to use, related tools. Lacks mention of error handling for missing keys, but annotations cover idempotency.
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 parameter 'key' is described in schema. Description does not add new semantic information beyond 'by key', so baseline 3 applies.
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?
Description explicitly states 'Delete a previously stored memory by key', clearly identifying the action and resource. It distinguishes itself from siblings by mentioning '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?
Provides specific when-to-use scenarios: context stale, task done, clear sensitive data. Also explicitly pairs with 'remember' and 'recall', offering alternatives.
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 near-duplicate lookup and prediction-market tools make selection ambiguous: ask_pipeworx_beta deliberately mirrors ask_pipeworx, and the five polymarket_* tools plus bet_research all target the same general 'should I bet / where is the edge' use case. The descriptions are detailed, but at the set level an agent must read extensive disambiguation essays to avoid picking the wrong tool.
The set is uniformly snake_case, and subfamilies like ask_pipeworx*, polymarket_*, and subscribe/unsubscribe are internally consistent. However, conventions vary widely: verb_noun (fetch_dataset, validate_claim), noun phrases (entity_profile, bet_research), bare verbs (remember, recall, forget), and prefix-branded meta tools (pipeworx_feedback, pipeworx_trending) all coexist without a single predictable pattern.
34 tools for a server nominally called 'Oecd' vastly exceeds the scope implied by the name and crosses the 25+ too-many threshold. Many tools belong to unrelated domains such as Polymarket arbitrage, npm dependency scanning, llms.txt generation, and AI visibility audits, making the set feel like a broad dumping ground rather than a focused tool server.
Within its sprawling domains the tool surface is fairly complete: lookup, grounded verification, deep research, entity resolution/profile/comparison, memory, subscriptions, alerts, and OECD dataflow search/list/fetch are all represented. There are minor gaps such as lack of direct OECD metadata descriptions or deeper navigation of the 5,708 underlying tools, but most workflows can be completed without dead ends.