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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description is free to spend its words on substance. It does: it discloses the decision taxonomy (CLEAR/REVIEW/BLOCK), the specific red flags detected, the fact that source coverage and links come back, and an explicit scope limitation that this is an analytical aid rather than authoritative FMCSA/insurance verification — a genuinely useful expectation-setter.

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?

Four sentences, no filler, and the actionable scoping (when to call, what it does) is front-loaded before the output description and the limitation caveat. Every clause carries new information about behavior or output.

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 no output schema and six inputs, the description carries the return contract itself — decision values, reasons, source coverage, primary links, and a verification checklist — plus the governing caveat. An agent knows both what it will get back and the limits of the answer before invoking.

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 100% and every parameter is documented in-schema (dot marked preferred, mc without prefix, format default, carrier_address used for the consistency check). The description mentions carrier resolution and 'the supplied tender context' but adds no syntax, precedence, or identifier-resolution rules beyond what the schema states, so the baseline 3 applies.

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?

States a specific verb and resource ('Screen a carrier'), pins the moment of use ('before accepting or dispatching a load'), and enumerates exactly which evidence classes are fused (FMCSA authority, insurance, safety, sanctions, court, federal awards). It reads distinctly from a raw lookup like fmcsa_carrier_lookup, but it never names a sibling, so the differentiation is inferential rather than explicit.

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 opening clause gives a clear when-to-use trigger (pre-tender/pre-dispatch screening), which is more than most tools offer. However, it never says when NOT to use it or which alternative fits better — carrier_vetting_score, carrier_vetting_evidence_pack, and carrier_monitor_recheck all sit in the same family with no routing guidance, and no prerequisites (e.g. what identifier is required) are stated.

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