Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only, and the description adds meaningful behavioral context: it counts only published articles, counts each language filing once, and explicitly disclaims quality or reach measurement. 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?

Three tightly written sentences carry purpose, usage examples, a scoping note, a conceptual caveat, and a sibling pointer. No filler; the key claim 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?

With a full output schema and read-only annotations already provided, the description gives everything needed for correct invocation: purpose, edition scoping, counting semantics, volume-vs-readership boundary, and downstream use with trendaz_news_list.

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%, so the schema already documents all four parameters with enums, defaults, date ranges, and limits. The description reinforces the 'all editions together' meaning and the 'most prolific first' ordering, but does not need to add more.

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, 'Rank', and a specific resource, 'Trend News Agency journalists', scoped by date range and edition. It also distinguishes itself from trendaz_trending by explicitly noting this measures volume, not readership.

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 concrete use cases ('who filed most today', 'how much did this desk publish last week') and an explicit routing alternative: trendaz_trending for readership questions. It even suggests passing a prolific byline id to trendaz_news_list, making adoption immediate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.