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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructiveHint=true. Description adds context about when deletion is appropriate (stale context, done task, sensitive data), which is helpful beyond the annotation.
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: one for purpose and one for usage. Every word earns its place; no redundancy.
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 destructive tool with one required parameter and no output schema, the description, annotations, and schema together provide complete guidance. Agent can confidently decide when and how to use it.
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?
Single parameter 'key' is described in the schema. The description does not add additional semantics beyond the schema, but schema coverage is 100% so baseline 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?
Description clearly states the verb ('Delete') and resource ('previously stored memory by key'). Distinguishes from siblings like 'remember' and 'recall' by specifying the delete action.
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 provides when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing 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.
ask_pipeworx and ask_pipeworx_beta are currently described as functionally identical, which is a direct ambiguity, and ai_visibility_check/scan_competitor_ai_presence plus the polymarket_* tools create several overlapping boundaries. The long descriptions help, but an agent still has to read deep into each one to avoid selecting the wrong tool.
Most tools use readable lowercase snake_case verb_noun names like discover_tools, resolve_entity, and validate_claim, but the set also includes bare nouns like gene and tissues, verb-only memory tools like remember/recall/forget, and noun-phrase names like entity_profile, recent_changes, and pipeworx_trending. The style is not chaotic, but no single convention is sustained.
36 tools exceeds the 25+ threshold and the surface is heavily padded with overlapping meta-tools, near-duplicate routers, and unrelated clusters such as Polymarket arbitrage, AI-visibility checks, and GTEx expression queries. For a server named Gtex, most of these tools are outside the apparent domain, making the count feel overgrown rather than well-scoped.
The GTEx-specific subset has only five tools and lacks obvious endpoints like multi-issue eQTLs, isoform expression, or sample-level querying, while the remaining 31 tools belong to unrelated Pipeworx, Polymarket, memory, and subscription domains. There is no coherent single purpose against which the surface can be considered complete, so agents will often hit dead ends or spend calls figuring out what the server is actually for.