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

The annotations already declare readOnlyHint=true and idempotentHint=true; the description is consistent with them and adds a meaningful behavioral guarantee: the tool reports row counts and latest row dates, so it gives freshness and coverage signals in one call. No contradiction.

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, front-loaded with the concrete substance (row counts, latest dated row, coverage) and then a crisp call-condition sentence. No filler; every clause 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?

With zero parameters and no output schema, the description supplies exactly what an agent needs to decide whether this tool answers a completeness question: what it returns, for which datasets, and when to call it. It does not need to restate annotations.

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?

Zero parameters, so there is nothing to disambiguate and no way to mis-invoke. The description clarifies what the output will cover (every dataset, entity-resolution coverage), which matters more than parameter docs here.

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 title 'What HillSignal has' and description 'Row counts and the latest dated row for every dataset behind these tools, plus entity-resolution coverage' make the purpose concrete: this is an introspective coverage-reporting tool. It distinguishes itself from siblings that answer domain questions because it reports on dataset completeness rather than the underlying data itself.

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 explicitly gives call conditions: 'Call it when an answer depends on how complete the data is, or before saying something does not exist.' This is exactly the kind of when-to-use guidance that beats the baseline; it also implicitly marks when not to call it (when you need the underlying content itself).

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