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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true; description adds the action 'delete' but no further behavioral details beyond the schema and 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, front-loaded with core action, zero unnecessary 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?
For a simple tool with one parameter and no output schema, the description fully covers purpose, usage conditions, and relationship to sibling tools.
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 description mentions 'by key', but the schema already defines 'Memory key to delete', so no additional value beyond baseline.
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?
Clearly states the tool deletes a memory by key, distinguishing it from siblings 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 specifies when to use (stale context, task done, clear sensitive data) and mentions companions, though no explicit 'when not to use'.
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, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical entry points (beta currently behaves exactly like stable), while entity_profile, recent_changes, and compare_entities all target company research. The prediction-market cluster (bet_research, polymarket_edges, polymarket_arbitrage, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) is large enough that an agent could easily select the wrong one.
Naming conventions are mixed throughout: verb_noun patterns (search_dois, list_repositories, validate_claim) coexist with noun phrases (entity_profile, recent_alerts, ai_visibility_check) and bare verbs (remember, recall, forget, subscribe). The only consistent thread is snake_case, but the grammatical style is unpredictable.
At 34 tools, the server is overstuffed, especially given its apparent focus is DataCite but only 3 tools actually serve that domain (get_doi, search_dois, list_repositories). The rest are a grab bag of Pipeworx data routing, prediction-market analytics, memory, and subscription utilities that would be better split into separate focused servers.
The DataCite surface is incomplete (no DOI creation, update, or deletion despite DataCite supporting registration), while the Pipeworx surface has no direct fetch-by-URI tool for the pipeworx:// citations that other tools return. The presence of a duplicate beta router and a beta router with no active differences further muddies the coverage picture.