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 declare destructiveHint=true and idempotentHint=true. Description adds context about what to delete and when, but does not disclose behavior for missing keys.
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 with no fluff; purpose is front-loaded and all information is relevant.
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?
Simple tool with one parameter, no output schema; description fully covers purpose, usage, and sibling relationships.
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 description only reiterates 'by key' without adding meaning beyond the schema.
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', distinguishing it 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?
Provides specific use cases (stale context, task done, clear sensitive data) and mentions pairing with siblings, but does not explicitly state when not to use or 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.
Most tools understandably fall into distinct clusters (BLS data, Polymarket, entity research, memory, subscriptions) and have detailed descriptions, but there is real overlap among the query entry points: ask_pipeworx and ask_pipeworx_beta are currently identical, and ask_pipeworx, deep_research, and validate_claim can all answer similar factual questions. The descriptions help an agent choose, but the set still contains more than a couple of near-duplicate paths.
All names are lowercase snake_case and several clusters share domain prefixes like bls_, polymarket_, and pipeworx_, which keeps the surface readable. However, the semantic naming pattern is mixed: verb+noun names like resolve_entity and list_subscriptions coexist with noun phrases like entity_profile, recent_alerts, and bls_latest, plus brand-led names like ask_pipeworx and polymarket_edges.
At 36 tools, the set is well past the 25+ threshold for a heavy tool surface, and several tools inflate the count: duplicate ask_pipeworx variants, multiple overlapping Polymarket scanners, and one-off meta helpers. The broad Pipeworx scope explains some of the breadth, but the redundancy makes the set feel bloated.
The set covers its core workflows well: data lookup, grounded verification, entity profiling and comparison, BLS series access, Polymarket research, subscriptions, memory, and feedback. Minor gaps remain, such as no subscription-editing tool, no dedicated citation-reader tool, and no general web-search tool, but ask_pipeworx acts as a catch-all router that lets agents work around most of them.