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 declare destructiveHint=true, and the description confirms 'delete' behavior. It adds context about clearing sensitive data and that memories are previously stored. No contradiction. Could mention error handling for nonexistent keys, but overall aligned with annotations.
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, no redundancy. Each sentence earns its place: one for core action, one for usage guidance. Efficient and clear.
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 low complexity (one parameter, no output schema) and annotations covering destructiveness, the description is sufficient. It provides purpose and usage cues. Could include a note on idempotency or error behavior for complete coverage, but not necessary for basic use.
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 parameter description ('Memory key to delete') is self-explanatory. The tool description adds no additional parameter insight beyond the schema. Baseline of 3 is appropriate.
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 defines the action (delete) and resource (memory by key). It distinguishes from siblings by pairing with 'remember' and 'recall'. The verb and resource are specific and unambiguous.
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 explicit when-to-use scenarios: stale context, task completion, or clearing sensitive data. Mentions pairing with siblings for context. Does not include when-not-to-use or alternatives beyond siblings, but the guidance is clear and practical.
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 functional space: ask_pipeworx_beta is explicitly identical to ask_pipeworx right now, and bet_research, polymarket_edges, and polymarket_arbitrage all target Polymarket opportunity detection. The detailed descriptions help, but an agent can easily select the wrong query/research or prediction-market tool.
Most names are readable snake_case and clusters like polymarket_* and pipeworx_* are internally consistent. However, the overall set mixes verb_object names (compare_entities, resolve_entity), bare verbs (forget, subscribe), and noun phrases (entity_profile, recent_alerts, top_exploited), so there is no unifying naming convention.
At 33 tools, the count exceeds the reasonable threshold for a focused server, and the problem is worse because the server is named Epss while most tools are Pipeworx data, Polymarket, memory, and subscription tools. A focused EPSS server would need only a handful of tools; this is a grab bag.
For the EPSS purpose implied by the server name, only get_epss and top_exploited exist, with no CVE search, historical score context, or vulnerability-management tooling. The unrelated research, memory, and prediction-market tools are individually fairly complete, but they do not fill the gap for the apparent EPSS use case.