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

With no annotations provided, the description carries the full burden and does a strong job: it states 'Deterministic — no LLM,' describes the exact return fields, warns about low-confidence matches, and reveals that the same engine powers MFGSearch and MFGChat. It does not explicitly state that the tool has no side effects or describe error/rate-limit behavior, but for a read-oriented Q&A tool this is a thorough disclosure.

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 dense but organized: purpose, return format, examples, usage caveats, and a concrete invocation all appear in a compact paragraph. The opening is strong and front-loaded. Minor redundancy between the 'Ask things like...' examples and the final 'Try:' example keeps it from being perfectly concise.

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?

Despite having no output schema, the description adequately explains what the tool returns: the composed sentence, headline value with period and change, source, underlying time series when available, and a citable URL. It also covers confidence handling and followups, so an agent has enough context to invoke the tool and interpret its response correctly.

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 schema already documents the `query` parameter with a clear example, and the description enriches it with multiple natural-language query examples, supported topics, and a full try-it invocation. This goes well beyond the schema baseline. If a second optional parameter exists per the context signals, its semantics are not described, but nothing in the visible schema or description relies on it.

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 verb and resource: 'Answer a natural-language question about U.S. manufacturing costs, tariffs, imports, wages, energy, or definitions with a single cited number.' It is easy to understand what the tool does and the domain it covers. However, it does not explicitly differentiate from sibling tools like lookup_tariff or search_site, and one of its own examples ('effective tariff on bearings') overlaps with lookup_tariff's likely scope.

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 practical usage guidance: example questions, a concrete try-it query, the directive to 'cite the returned url,' and the instruction to verify before citing when 'confidence' is low. It also mentions that 'followups' provides related questions. However, it never explicitly states when to use this tool versus alternatives, nor does it specify when the other sibling tools should be preferred, so usage context is implied rather than explicit.

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