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, so the description's 'Delete' aligns. The description adds no further behavioral context beyond 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?
Two sentences, no wasted words. The first sentence immediately states the purpose, and the second provides usage guidance.
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 1-parameter tool with no output schema, the description covers purpose, usage context, and pairing with siblings. It lacks mention of irreversibility, but that's implied by destructiveHint.
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 schema already describes the 'key' parameter as 'Memory key to delete'. The description adds no additional semantic value.
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 action ('Delete') and resource ('previously stored memory by key'). It distinguishes from siblings 'remember' and 'recall' by specifying the deletion purpose.
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 explicitly lists three scenarios for use: stale context, task completion, clearing sensitive data. It also mentions pairing with siblings, but does not explicitly state when not to use.
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.
Many tools have closely related or overlapping purposes: ask_pipeworx, ask_pipeworx_beta (currently identical), and ask_pipeworx_grounded all route to the same underlying toolset, while discover_tools and suggest_questions both help agents discover capabilities. The polymarket_* family also has several opportunity-scanning tools with subtle differences, though detailed descriptions help clarify.
Names are mostly snake_case but follow mixed patterns: verb-first (ask_pipeworx, validate_claim), noun-first (entity_profile, bet_research, la_recent), and bare verbs (remember, forget, unsubscribe). The prefix groups (la_, pipeworx_, polymarket_) show some consistency, but there is no uniform verb_noun convention.
34 tools is well into the 'too many' range for a single server. The surface bundles several distinct domains—structured data querying, prediction markets, LA open data, memory, subscriptions, and npm scanning—making it feel like a kitchen sink rather than a focused toolset.
Within each bundled sub-domain, coverage is strong: query/grounded/research/entity-profile/compare/validate covers data workflows; polymarket tools include research, edge scan, arbitrage, fill-risk, and cross-venue spread; LA data has search/query/recent; memory and subscription lifecycles are fully CRUD. Minor gaps exist (e.g., no way to browse LA dataset attributes beyond search), but no major dead ends.