recentBlocklist entries first seen in the last N hours.
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | Default 24, max 720 (30 days). |
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | Number of entries first seen within the window | |
| hours | Yes | Number of hours in the lookback window | |
| results | Yes | Blocklist entries first seen in the time window |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and destructiveHint=false, so the description adds value by specifying the temporal filter but does not elaborate on pagination or ordering. 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?
Single sentence, front-loaded, no redundant information. Every word earns its place.
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 filtered list tool with one optional parameter and an output schema, the description is sufficient. It covers the core functionality without missing essential details.
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 hours parameter documented. The description adds no extra semantic meaning beyond the schema, 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 clearly states the tool lists 'Blocklist entries first seen in the last N hours,' providing a specific verb (list implied), resource (blocklist entries), and scope (recent entries). This distinguishes it from siblings like 'recent_alerts' or 'recent_changes'.
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?
No explicit guidance on when to use this tool versus alternatives. While the description implies use for recent blocklist entries, it does not mention exclusions or related tools, leaving the agent to infer context.
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 occupy the same conceptual space: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all answer 'what can this server do' or 'look this up' in overlapping ways. The Polymarket suite (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) and the memory trio (remember, recall, forget) also create boundary confusion despite long descriptions.
Naming is a mixed bag: some tools are imperative verbs (check_ip, forget, remember, validate_claim), some are bare nouns or adjectives (list, recent, aggressive), and many are noun compounds (entity_profile, polymarket_edges, pipeworx_trending). No consistent verb_noun or domain-prefix pattern holds across the set.
35 tools is excessive for a server ostensibly named Feodotracker, whose core blocklist surface is only four tools (list, recent, aggressive, check_ip). The rest is a sprawling collection of unrelated Pipeworx, Polymarket, memory, subscription, and utility features that would be better split into separate servers.
The core blocklist domain is minimally covered: you can list, filter by family/status, check an IP, and see recent additions, which covers basic read-only use. However, there are notable gaps and dead ends, such as no historical lookup beyond recent hours and no per-IP detail beyond membership, while the bundled Pipeworx/Polymarket features are thorough but make the overall surface feel scattershot.