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 idempotentHint=true. The description adds little beyond the obvious 'Delete' action, but it does clarify that it removes previously stored memory and can be used to clear sensitive data. No contradiction 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 short sentences deliver the essential info: what it does, when to use it, and related tools. Every word earns its place, and the critical verb 'Delete' is front-loaded.
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 one-parameter destructive tool, the description covers the what, when, and related operations. No output schema is needed for a delete operation, and the usage guidance is sufficient. Minor gap: no mention of behavior for non-existent keys, but idempotentHint covers that implicitly.
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 the key parameter described as 'Memory key to delete.' The description adds no extra detail about the parameter beyond what the schema already provides, so the baseline of 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 opens with a specific verb and resource: 'Delete a previously stored memory by key.' This clearly distinguishes it from sibling tools like remember and recall, which are explicitly mentioned as counterparts.
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?
It provides explicit use cases: stale context, task completion, or clearing sensitive data. It also mentions pairing with remember and recall. However, it does not explicitly state when not to use the tool or name alternative tools as a primary choice.
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.
The tool set is a chaotic mix of unrelated domains: Oregon Open Data tools (datasets, metadata, query) are buried among dozens of tools for Pipeworx general query, Polymarket betting, memory management, and AI visibility. Many tools have overlapping purposes (e.g., ask_pipeworx, ask_pipeworx_grounded, deep_research, validate_claim) making it impossible for an agent to distinguish the right tool for a given task without deep inspection.
Naming is wildly inconsistent: snake_case (ai_visibility_check, pipeworx_feedback), camelCase (bet_research, datasets, metadata, query), mixed (ask_pipeworx_grounded, polymarket_arbitrage). No consistent verb_noun or pattern exists, and many names are vague (remember, recall, forget) without connection to the server's assumed domain.
33 tools is excessive for a server ostensibly about Oregon Open Data, which only has 3 relevant tools. The remaining 30 are from other services (Pipeworx, Polymarket, etc.) and do not belong, making the count inappropriate for the server's declared purpose.
For the Oregon Open Data domain, the surface is bare: only search, metadata, and query. Missing operations like upload, update, or delete datasets. The heavy presence of unrelated tools (betting, memory, AI visibility) does not compensate for the gap in the actual domain coverage.