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

Annotations already declare this is not read-only, not idempotent, not destructive, and closed-world, so the safety profile is partly covered. The description usefully adds that missing observations remain unknown and that successful deliveries are saved privately and consume shared research credits, but it omits other operational traits such as delivery persistence details or retry behavior.

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 front-loaded with the core purpose and uses dense sentences with little obvious padding. Some phrases are telegraphic and under-explained, but each sentence generally contributes a useful behavioral or parameter detail.

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?

This is a complex tool with nine parameters, nested objects, low schema description coverage, and several modes such as fresh versus captured basis. The description does not provide enough operational context for an agent to confidently construct a request without consulting additional documentation.

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 description coverage is only 22%, so the description carries a heavy burden for explaining parameters. It clarifies a few grouping and top behavior details, but leaves major inputs like basis modes, retain, delivery, metrics selection, comparisons, order, windows, and most selector kinds unexplained.

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 states the tool produces full-scope counts, engagement metrics, and comparisons, which is a clear high-level purpose. It does not explicitly name competing siblings like discover_evidence or read_evidence, so an agent still has to infer the boundary between measuring versus reading or discovering evidence.

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?

There is conditional guidance for specific group_by values, such as asset_selected requiring a positive selector and asset_all_attached grouping every attached asset. However, it never states when to use measure_evidence instead of siblings like discover_evidence, read_evidence, or resolve_assets, and it provides no clear when-not guidance.

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