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 reinforcing the destructive nature, but does not introduce new behavioral traits 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?
Three sentences, no wasted words. The action and key detail are front-loaded, making it efficient to parse.
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 parameter, no output schema, and destructive behavior, the description fully covers what it does, when to use, and related tools. No gaps.
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 describes 'key' as 'Memory key to delete'. The description only mentions 'by key' without adding meaning beyond the schema, 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?
Explicitly states 'Delete a previously stored memory by key', providing a specific verb and resource. Mentions pairing with remember and recall, distinguishing its function from siblings.
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?
Clearly specifies when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also recommends pairing with remember and recall, offering guidance on 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.
The DMV-specific tools are individually distinct, but they are buried among ~30 unrelated Pipeworx utilities with several overlapping pairs (ask_pipeworx variants, entity_profile/compare_entities/recent_changes, and the polymarket suite). An agent pointed at this server cannot reliably tell which tools belong to the California DMV domain versus the general data platform.
Most tools use lowercase snake_case, and the ca_dmv_* family is consistent, but there is no coherent semantic pattern across the set: some names are noun phrases (entity_profile), some verb phrases (discover_tools, validate_claim), and many are product-specific prefixes (ask_pipeworx, polymarket_*). The formatting is consistent, but the naming conventions are mixed.
37 tools is far too many for a California DMV server; only 6 are actually DMV-specific. The remaining ~30 tools cover general Pipeworx data lookup, prediction markets, memory, subscriptions, and AI visibility, which belong in a separate server entirely.
For the stated DMV scope, the surface is thin: it covers registrations, licenses, offices, forms, insurance codes, and EV adoption, but misses common DMV queries like registration fees, title/status lookups, and appointment or transaction data. The 30 unrelated tools do not fill these domain gaps and instead obscure them.