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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: deterministic fixed rules rather than a model, the three possible verdicts, per-requirement plain-English reasons, and the critical safety property that anything unreported, unreadable, or below 0.7 confidence goes to needs_review rather than silently passing.

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 dense sentences, front-loaded with purpose, then self-read instruction, then verdict semantics, then the fail-safe routing rule. Every sentence carries information; the only mild redundancy is the enumeration of check categories, which partially overlaps the requirements schema.

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?

No output schema exists, so the description must describe the return — and it does, naming the verdict values and the per-requirement reason string. Combined with the routing rule and the confidence threshold behavior, an agent has everything needed to call this 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?

Schema coverage is 100%, so the baseline is 3; the description adds provenance semantics by tying the `requirements` object to build_insurance_requirements and presenting `preset` as the alternative source, plus the as-of framing. It does not restate the preset contents or confidence thresholds, but the schema already carries those.

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 (checks an ACORD 25 certificate of insurance) and enumerates exactly what is checked: coverage presence, limits, expiry, endorsements. It is clearly distinguishable from sibling build_insurance_requirements, which produces the requirements rather than evaluating against them.

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?

Explicitly directs the agent to read the certificate itself and pass what it shows, and names the two acceptable sources of requirements: 'preset or the requirements object from build_insurance_requirements.' This routes the agent to the sibling tool for the non-preset path rather than leaving it to inference.

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