content_decay

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

With no annotations, the description carries the burden. It adds important behavioral rules: base analysis only on returned data, report exact numbers, avoid speculation about causes, and acknowledge insufficient data. It also mandates a rich presentation style. Yet it does not disclose return structure, rate limits, or read-only status, leaving some gaps.

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 longer than typical but well-structured with a clear definition, measurement rule, important analytical constraints, and presentation guidelines. Every sentence serves a purpose, and it is front-loaded with the main intent, making it efficiently scannable.

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?

Given the absence of output schema and annotations, the description compensates by defining not only the tool's logic but also how to interpret and present results (e.g., summary cards, color-coded indicators, tabbed sections). It hints at output categories through 'different categories of results' but does not enumerate specific data fields, which is a minor 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?

The tool has zero parameters, so baseline 4 is appropriate. The description adds context about the tool's selection logic (three consecutive 30-day periods) which is not parameter-specific but provides semantic meaning beyond the empty schema.

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's purpose: finding pages with consistent traffic decline over three consecutive 30-day periods. It uses a specific verb ('Find') and resource ('pages'), and the decline criterion distinguishes it from siblings like traffic_drops or quick_wins.

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 provides a clear usage condition: only use when looking for multi-month consistent declines, and explicitly says 'One bad month is noise' to indicate when the tool is not appropriate. However, it does not name alternative sibling tools or explicitly state exclusions beyond the statistical threshold.

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