top_articlesArticles on the current site that generated the most commission over a window. URL grouping strips tracking parameters so the same article with different ?gclid= values is counted together. Use this to answer "which posts make money" and "where should I spend editorial time".
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Window size in days (default 30). | |
| limit | No | Max articles to return (default 10). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses important behavior: URL grouping strips tracking parameters like gclid. No annotations provided, so description carries full burden but does not cover query scope (e.g., read-only, no side effects) or rate limits. Adequate but not exhaustive.
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: first states purpose, second provides behavioral detail and usage guidance. No redundancy, front-loaded. Every sentence adds value.
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?
Parameters well-covered. Missing explicit statement about ranking order (descending by commission) and window end point (e.g., last N days including today). However, tool is simple and output likely obvious. Good enough for effective use.
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 both parameters with descriptions. Description adds semantic context: explains how the grouping of URLs (stripping tracking params) affects article counting. This helps agent understand parameter impact beyond schema basics.
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?
Describes exact resource ('articles on current site'), action ('most commission over window'), and unique behavior (URL grouping). Distinguishes clearly from siblings like at_risk_articles or revenue_summary.
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 use cases ('which posts make money', 'where to spend editorial time'). Does not specify when not to use, but the purpose is narrow enough. Could mention alternatives like revenue_summary for broader earnings view.
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.
Each tool has a distinct purpose: at_risk_articles combines broken links with revenue loss, broken_links lists all broken links, revenue_summary gives revenue data, suggest_replacement finds alternatives, and top_articles shows top earners. There is no overlap.
All tool names follow a consistent snake_case pattern with descriptive terms like adjective_noun (at_risk_articles, broken_links) or verb_noun (suggest_replacement). No mixing of conventions.
5 tools is well-scoped for a server focused on affiliate link management and revenue optimization. Each tool serves a clear purpose without redundancy.
The set covers finding broken links, assessing revenue impact, and suggesting replacements, but lacks an 'apply_fix' tool to actually implement changes, which is mentioned as v1.1. Missing update/delete functionality for links.