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 and idempotentHint=true, so the description does not need to restate safety. It adds minimal behavioral context ('clear sensitive data') but does not disclose potential error behavior or return value. This is consistent with annotations, and the description carries only light extra weight beyond what annotations provide.
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?
The description is three concise sentences: a clear operation statement, usage conditions, and a sibling pairing note. Every sentence earns its place, and the most important information 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 single-parameter delete tool with annotations covering destructive and idempotent traits, the description covers purpose, usage timing, and related tools. It does not mention return behavior, but given the tool's simplicity and lack of output schema, this is not a significant gap.
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% (one param 'key' with description 'Memory key to delete'). The description merely repeats 'by key' without adding semantic detail beyond the schema, so it meets the baseline but adds no extra value.
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.' It clearly distinguishes this tool from its siblings (remember and recall) by specifying the delete operation, and the addition of 'by key' indicates the target mechanism.
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?
The description gives explicit usage conditions: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also references siblings with 'Pair with remember and recall,' providing clear situational guidance.
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 tool clusters have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer factual questions; polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, and polymarket_kalshi_spread all analyze prediction-market opportunities; discover_tools and suggest_questions both serve as meta-tool onboarding. An agent could easily pick the wrong variant.
Most tools use snake_case, but naming patterns are mixed: some are verb_noun (get_flood_forecast, list_subscriptions), some are noun-centric (entity_profile, bet_research), some are bare verbs (remember, recall, forget), and some use long descriptive phrases (ask_pipeworx_grounded, polymarket_kalshi_spread). It is readable but lacks a single predictable convention.
33 tools is heavy for a server whose apparent core is flood forecasting — only 2 of 33 tools (get_flood_forecast, get_river_discharge) relate to flooding. The bulk is a sprawling Pipeworx data-access, prediction-market, and memory layer, making the surface feel overstuffed and off-topic relative to the server name.
If the intended domain is flood data, the surface is severely incomplete: only forecast and discharge lookups exist, with no historical flood events, alert subscriptions, mapping, or severity-warning tools. If instead the domain is meant to be Pipeworx-style data research, the surface is broad but still has gaps (no direct SEC filing text retrieval, no clear update/delete lifecycle for many resources). Either way, the purpose is unclear and coverage is mismatched.