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?
Description confirms destructive nature (matches destructiveHint=true) and adds context about clearing sensitive data. Annotations already cover destructive hint; description adds moderate extra context but no detail on side effects or errors.
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 plus a pairing note, front-loaded with action and resource. No wasted words, highly efficient.
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 single-parameter deletion tool with no output schema, description covers use cases and pairing. Lacks details on post-deletion behavior or error handling but 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 parameter 'key' described as 'Memory key to delete.' Description adds no additional meaning beyond what schema provides, baseline 3.
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 'Delete a previously stored memory by key,' specifying verb, resource, and scope. Distinguishes from siblings 'remember' and 'recall' by naming them explicitly.
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 says when to use (stale context, task done, clear sensitive data) and pairs with remember and recall. No explicit when-not or alternatives, but clear context provided.
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 tools occupy overlapping roles: ask_pipeworx and ask_pipeworx_beta are currently identical, ask_pipeworx_grounded/deep_research/validate_claim all provide grounded answering, and bet_research/polymarket_edges/polymarket_arbitrage all surface betting opportunities. The descriptions are detailed, but the boundaries between routers and research modes are fuzzy enough that an agent could easily select the wrong one. The taxonomy, memory, and subscription clusters are distinct, but they are drowned out by the overlapping meta-tools.
All names use snake_case, which provides some visual consistency, but the verb_noun pattern is not consistently applied: search_taxa/get_hierarchy are clean verb_noun, while deep_research, entity_profile, polymarket_edges, and bet_research are noun-ish or reversed patterns. There is good family-level consistency within ask_pipeworx_* and polymarket_*, but the overall set mixes conventions and requires reading descriptions to infer what each tool does.
34 tools is well over the 25-tool threshold and reflects a sprawling multi-domain server spanning taxonomy, structured-data lookup, prediction markets, subscriptions, memory, and AI visibility. Each cluster may be individually reasonable, but as a single MCP surface it is too heavy and forces agents to filter through many irrelevant tools.
For the broad data-research and prediction-market purpose, the surface is fairly complete: it covers routing, grounded answers, deep multi-source research, entity profiles, comparisons, claim validation, entity resolution, subscriptions, alerts, memory, and market edge/fill checks. Minor gaps exist—no direct web-search tool, the beta router adds no current behavior, and some patent endpoints soft-fail—but agents can generally work around them.