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 set destructiveHint=true, so the description's 'Delete' is consistent. It adds context about clearing sensitive data, which is a behavioral trait beyond the annotation's binary flag.
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 wasted words. The verb and object are front-loaded, and usage guidance follows efficiently.
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 delete operation with one parameter, the description covers purpose, usage guidance, and pairing with sibling tools. No output schema needed given the action is straightforward.
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 covers the single parameter with description 'Memory key to delete'. The description doesn't add new parameter info, so baseline 3 is appropriate given 100% schema coverage.
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 starts with 'Delete a previously stored memory by key', which is a specific verb and resource. It clearly distinguishes from siblings (remember and recall) by focusing on deletion.
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 states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. It also names sibling tools as alternatives for storing/recalling.
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.
There are multiple severe overlap clusters. ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route to the same 5,578 tools, and ask_pipeworx_beta explicitly states it 'currently matches ask_pipeworx exactly' — a direct ambiguity. The six polymarket_* tools plus bet_research form another dense, hard-to-distinguish cluster, and entity_profile/recent_changes/compare_entities/resolve_entity all have overlapping entity-investigation purposes. The long descriptions help but an agent would frequently misselect.
The dominant families are internally consistent (polymarket_* prefix, ask_pipeworx_* suffix family, and the verb-based remember/recall/forget), which aids navigation. However, the overall set mixes several conventions: single-word nouns (query, datasets, metadata, recall), verb_noun compounds (validate_claim, generate_llms_txt), and domain_noun names (entity_profile, polymarket_edges). Readable, but there is no unified pattern across the server.
34 tools is clearly over the 25-threshold for heaviness, and several earn little distinct value: ask_pipeworx_beta is a live duplicate of ask_pipeworx, the five-algorithm Polymarket family could be consolidated, and meta/utility tools (suggest_questions, discover_tools, pipeworx_trending, generate_llms_txt, scan_dependency) feel bolted on rather than essential. The breadth of the data domain justifies some size, but the redundancy and tangents push it into bloat.
Within its core sub-domains the surface is fairly complete: company research has resolve→profile/compare→recent_changes→validate_claim as a full lifecycle, subscriptions have subscribe/unsubscribe/list/recent_alerts, and memory has remember/recall/forget. The Polymarket workflow is especially thorough (detect→verify→fill-risk→track-decay). However, the server's stated identity ('Data Michigan') is barely served — the Michigan Open Data surface is only search/schema/query with no update or write path — and the scatter of unrelated tools (npm dependency scan, llms.txt generation) makes the overall purpose incoherent, so gaps are hard to evaluate.