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 provide destructiveHint=true; description adds context for why deletion is used (stale data, sensitive data), going beyond the annotation without contradicting it.
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 compact sentences with no wasted words; action and context are front-loaded.
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 one-parameter tool with strong annotations and schema, the description covers all necessary context: purpose, when to use, and relationship to siblings.
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 clear description of 'key' parameter. Description does not add extra meaning beyond schema, so baseline score of 3 is appropriate.
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 states 'Delete a previously stored memory by key' – a specific verb and resource. It distinguishes from sibling tools like 'remember' and 'recall' by naming them.
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 states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also directs to pair with 'remember' and 'recall', indicating 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 tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-duplicates, while deep_research, discover_tools, and suggest_questions blur the line between routing, research, and discovery. The six polymarket_* tools plus bet_research also create a dense cluster where agents could easily select the wrong one. Individual descriptions are detailed, but the set boundaries are not crisp.
Names are mostly consistent lowercase snake_case with a verb-first pattern such as list_locations, search_datasets, resolve_entity, and validate_claim. A few exceptions like dataset_details, entity_profile, and pipeworx_trending break the verb_noun convention, but the style is predictable and readable overall.
35 tools is heavy for a single MCP server, especially when several are explicitly redundant (ask_pipeworx_beta) or near-overlapping meta-routers. The count feels inflated by duplicated capabilities and a large prediction-market family rather than by genuinely distinct operations.
The broad Pipeworx surface is fairly complete: entity profiles, comparisons, claim verification, memory, subscriptions, and grounded lookups are all represented. However, the server is named Hdx and the actual HDX-specific surface is thin — search_datasets and dataset_details exist, but there is no organization detail, no resource download flow, and no way to manage HDX data beyond browsing.