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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely non-structured context: no authentication is required and the call is free, which matters for an agent operating under a USDC budget. It does not disclose sample size, row count, or which columns are included, which is the main behavioral gap.

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 short sentences with the key qualifiers ('free', 'unauthenticated', 'sample') front-loaded in the first line. The second sentence earns its place by explaining the commercial rationale. Minor waste from the line break splitting a single thought, but nothing extraneous.

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?

There is no output schema, so the description carries the burden of explaining what comes back, and it only says 'carrier_profile rows' without stating how many rows or whether the sample shares the paid tools' full column set. For a zero-parameter preview tool this is close to adequate, but an agent cannot judge representativeness from the description alone.

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 takes zero parameters, so there is no parameter meaning to convey and the baseline of 4 applies. The description correctly implies no filtering arguments are accepted, since it presents the call as an unconditional sample fetch.

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 names the resource precisely ('carrier_profile rows') and the delivery mode ('free, unauthenticated sample'), so an agent knows exactly what it returns. It distinguishes itself from the paid siblings by framing itself as the pre-purchase evaluation path, though it never names a specific paid alternative such as lookup_carrier or search_carriers.

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?

It gives a clear triggering condition: use this to evaluate data quality before spending USDC on the paid tools. That is an actionable when-to-use rule tied to a cost decision. It stops short of an explicit 'do not use this when you need the full dataset' exclusion, but the 'sample' framing implies it.

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