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 idempotentHint=true, covering safety. Description adds no new behavioral traits beyond stating 'delete', which is consistent but not additive.
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, first sentence front-loads the purpose. No wasted words.
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 the single required parameter, annotations covering destructive behavior, and no output schema, the description is complete and sufficient.
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% with description 'Memory key to delete'. Description does not add meaning beyond 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?
The description clearly states the verb 'Delete', the resource 'previously stored memory', and the method 'by key'. This distinguishes it from sibling tools 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?
Explicitly lists when to use: 'context is stale', 'task is done', 'clear sensitive data'. Also references 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.
Most tools have distinct, well-scoped purposes, but several question-answering/research tools sit close together: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim can all be selected for factual questions. The descriptions are detailed enough to reduce ambiguity, but ask_pipeworx_beta is currently identical to ask_pipeworx, and discovery helpers like discover_tools, suggest_questions, and pipeworx_trending also overlap somewhat.
Names are uniformly snake_case and mostly follow a verb_noun pattern such as build_url, list_subscriptions, resolve_entity, and validate_claim. The polymarket_* and pipeworx_* prefixes form a readable convention, though a few names like pipeworx_feedback and polymarket_arbitrage are noun-phrases rather than verb-first actions.
34 tools is well past the 25+ threshold where even a broad platform starts to feel bloated. The set mixes data research, prediction-market tooling, URL utilities, memory, subscriptions, feedback, and npm scanning, which would be more coherently split across focused servers.
The core research workflows are thoroughly covered: routing, grounded answers, deep research, entity resolution, comparisons, claim validation, discovery, alerts, and memory all exist. However, the URL utility and dependency-scanning side domains feel tacked on and incomplete, and there is no dedicated tool to fetch an arbitrary pipeworx:// citation record even though such URIs are returned throughout.