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 stale context, enhancing transparency beyond annotations without contradiction.
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 concise sentences: purpose, usage guidelines, and sibling pairing. No redundant or irrelevant content; each sentence serves a clear function.
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?
Given a simple tool with one parameter, no output schema, and informative annotations, the description covers purpose, usage, and relationships completely.
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% for the single parameter 'key,' which is adequately described in the schema. The description adds minimal parameter detail beyond 'by key,' so 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?
The description clearly states 'Delete a previously stored memory by key,' specifying the verb and resource. It also naturally distinguishes from sibling tools remember and recall by implying storage and retrieval functions.
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 gives explicit when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also advises pairing with remember and recall, though it 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.
Several tool families have unclear boundaries: ask_pipeworx_beta is explicitly identical to ask_pipeworx right now, ask_pipeworx_grounded and validate_claim both verify claims against sources, and polymarket_edges/polymarket_arbitrage/bet_research all surface prediction-market opportunities. Agents would need to read very long descriptions to distinguish overlapping intents, and would likely misroute requests.
All names use snake_case, which is a consistent base, and subgroups (shodan_host*, ask_pipeworx*, polymarket_*) follow internal patterns. However, conventions mix verb-first (ask_pipeworx, validate_claim, resolve_entity) with noun-first (entity_profile, bet_research, recent_alerts), and parallel functionality is named with inverted ordering (ai_visibility_check vs scan_competitor_ai_presence).
34 tools is above the comfortable range for a single server and the breadth feels bloated, especially with five highly niche Polymarket tools. More critically, the server is named 'Shodan' but only 3 of 34 tools are Shodan-related, so the count is badly mismatched with the stated identity.
For a server claiming to be Shodan, the surface is severely incomplete — only host lookup, search, and count are present, with no DNS, alerting, or other standard Shodan operations. For the actual Pipeworx/Polymarket domain implied by most tools, coverage is fuller but still has gaps such as no direct tool to fetch a pipeworx:// citation URI, and the memory/subscription features feel bolted on rather than integral.