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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, and the description adds what they cannot: the default value of every rule, the exact threshold semantics (max_risk_score above → needs_review, block_reason_codes present → ineligible), the full return shape, and the one-lookup cost. That is substantive behavioral context beyond the structured fields.

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?

Front-loaded with the purpose and outcome vocabulary, then the rule list, then the escalation caveat and cost. Sentences are dense but every clause carries information an agent needs; the semicolon-separated rule enumeration is the most economical way to convey nine parameters and their verdict mappings.

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?

For a nested three-parameter tool with no output schema, the description covers input alternatives, default rule behavior, all three outcome states, the per-rule result and reason payload, and the collateral verdict and risk score. Nothing an agent needs in order to call it correctly and interpret the response is absent.

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?

Although schema description coverage is nominally 100%, the nested properties under `rules` carry no per-property descriptions at all, so the description is doing real work by explaining follow_verdict, require_active_authority, max_risk_score, block_reason_codes and the rest, including their defaults and which verdict each triggers. It also states the mutual-exclusion constraint ("Pass exactly one of dot or mc") that the schema cannot express.

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 opens with a specific verb and resource ("Evaluate your own load rules against a carrier") and immediately enumerates the three possible outcomes plus the CarrierVet verdict and risk score that come back. This tells an agent exactly how it differs from sibling tools like lookup_carrier or get_risk, which return raw data rather than a rules-based decision.

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?

Strong workflow guidance: "Escalate needs_review and ineligible to a human; the decision to tender is theirs" tells the agent when not to act autonomously, and "Costs 1 lookup" gives a cost signal for deciding whether to call. What's missing is explicit routing against siblings — it never says when to prefer lookup_carrier or get_risk instead of this tool.

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