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 and readOnlyHint=false, so the description correct that this is a destructive write operation. The term 'delete' is consistent. No additional behavioral details about idempotency or missing keys are provided, but annotations already cover the key aspects.
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 efficient sentences: one for the core action, one for usage context. No wasted words. Front-loads the purpose. Ideal conciseness.
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 deletion tool with one parameter and no output schema, the description is sufficiently complete. It covers purpose, usage context, and sibling relationships. Minor omission: no mention of return value or error behavior, but this is acceptable for such a straightforward operation.
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 description adds no extra parameter meaning beyond the schema's 'Memory key to delete'. Baseline 3 is appropriate as the schema already fully documents the single parameter.
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.' The verb 'delete' is specific and the resource is precisely identified. This distinguishes it effectively from siblings like 'remember' and 'recall'.
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?
Explicit guidance is given: 'Use when context is stale, the task is done, or you want to clear sensitive data...' and it recommends pairing with siblings 'remember' and 'recall', leaving no ambiguity about when to use this tool.
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.
Most tools have clearly distinct purposes, but the set is large and several boundaries are fuzzy: ask_pipeworx_beta is currently identical to ask_pipeworx, and the five polymarket_* tools plus ai_visibility_check/scan_competitor_ai_presence create selection ambiguity. The exhaustive descriptions mitigate confusion, but an agent could still easily pick the wrong variant.
All tool names use snake_case and most follow a verb_noun pattern (get_gene, search_genes, validate_claim, subscribe/unsubscribe, compare_entities). The deviations are minor and internally consistent: noun-first family names like polymarket_edges/entity_profile and the ask_pipeworx_* variant group.
34 tools is well above the comfortable range, and the server is named Hgnc while only 3 of its tools actually concern HGNC genes. The Pipeworx platform is bolted onto what should be a narrow gene-lookup surface, making the set feel bloated and mis-scoped.
For the HGNC domain, search_genes → get_gene → resolve_xref covers the core lookup lifecycle well. For the broader Pipeworx functionality the surface is remarkably thorough, with ask, grounded, deep research, compare, validate, subscribe, and memory tools leaving only minor gaps such as batch gene listing.