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 provide destructiveHint=true, idempotentHint=true, readOnlyHint=false. Description adds context about clearing stale or sensitive data, but does not contradict annotations. No additional behavioral details beyond use cases.
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 and purpose, no filler. Every sentence adds value.
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 required parameter and no output schema, the description is complete. It explains the action, use cases, and relationship to sibling tools.
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 one parameter 'key' described as 'Memory key to delete'. Description adds no further semantics beyond the schema. Baseline 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 clearly states 'Delete a previously stored memory by key.' The verb 'delete' and resource 'memory' are specific. It also implicitly distinguishes from siblings 'remember' and 'recall' by referencing 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 the agent saved earlier.' Provides alternatives by mentioning 'Pair with remember and recall.'
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.
Multiple tool clusters overlap heavily — ask_pipeworx_beta is functionally identical to ask_pipeworx right now, and the six Polymarket tools (polymarket_edges, polymarket_arbitrage, bet_research, etc.) have blurry boundaries. The entity-research family (entity_profar, compare_entities, recent_changes) is also easy to misselect despite detailed descriptions.
All names are snake_case, but conventions are mixed: verb_noun (resolve_entaty, validate_claim), bare verbs (remember, recall, query), adjective_noun (recent_alerts, recent_changes), and brand-prefixed nouns (polymarket_edges, pipeworx_trending). Family prefixes and verbs help readability, but the overall pattern is not uniform.
At 34 tools this exceeds the 25+ threshold and spans loosely related domains — Bloomington open data, Pipeworx research, prediction markets, AI marketing, memory, npm scanning, and llms.txt generation. The scope feels heavy and unfocused relative to the 'Data Bloomington' server name.
The core research lifecycle is well covered: routing (ask_pipeworx), grounded verification, deep research, entity profiles/comparisons/changes, claim validation, entity resolution, subscriptions, and memory all exist. Minor gaps remain — no standalone tool for fetching a pipeworx:// citation URI and no API-key management — but agents can work around them.