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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate destructive behavior. The description adds useful context about why to delete (stale context, done tasks, sensitive data) beyond what annotations provide, but no contradictions.
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?
Three concise sentences front-load the purpose, then usage guidelines, then related tools. No wasted 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 delete operation with one required parameter and no output schema, the description is complete: it explains what, when, and how it relates to other 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% with the 'key' parameter described as 'Memory key to delete'. The description adds 'by key' but no additional detail beyond the schema, meeting the 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?
The description clearly states 'Delete a previously stored memory by key' with a specific verb and resource. It distinguishes itself from siblings by mentioning '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 states when to use (context is stale, task done, clear sensitive data) and pairs with related tools (remember, recall), providing clear 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.
Multiple tools overlap heavily: ask_pipeworx, ask_pipeworx_beta (explicitly identical when no routing candidate is active), ask_pipeworx_grounded, deep_research, and validate_claim all answer factual questions through the same underlying router. The prediction-market cluster (polymarket_edges, polymarket_arbitrage, bet_research, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) has substantial purpose overlap that requires reading long descriptions to disambiguate.
Mostly snake_case, and the pipeworx_/polymarket_/ask_ prefixes give some structure, but conventions are mixed: some tools are verb_noun (list_municipalities, get_data), some are bare verbs (forget, recall, remember), and some are noun phrases (entity_profile, deep_research, bet_research, recent_changes). The inconsistent prefixing across meta-tools (ask_, deep_, entity_, scan_, validate_) makes the surface feel less predictable than it could be.
35 tools is on the heavy side, but the bigger problem is that the server name 'Kolada Se' matches only 4 tools (search_kpi, list_municipalities, list_org_units, get_data), while the other 31 tools belong to unrelated domains (Pipeworx data routing, prediction markets, memory, subscriptions, AI visibility). This is a severe scope mismatch that makes the count feel bloated and unfocused.
For the Kolada domain named by the server, the surface is minimal: you can search KPIs, list municipalities, list org units, and fetch single-KPI data, but there is no multi-year bulk fetch, cross-municipality comparison, or unit-level data retrieval. The broader Pipeworx/prediction-market surface is fairly feature-complete, but it is not what the server name implies, so the set as a whole leaves the apparent domain thinly covered.