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

With no annotations, the description carries the full burden. It usefully discloses the key-tier gating, that results include 'coverage boundaries' (i.e. rate ranges it cannot audit), and provenance — real behavioral value. However, it says nothing about whether the call is read-only, what happens to unsupported HTS lines, or error behavior on oversized/malformed line sets, which matters for a tool with a 200-line nested payload.

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 sentences, no filler, front-loaded with the access prerequisite followed by the action and return shape. Slightly imperfect ordering — the operational behavior matters more than the key tier to an agent deciding whether to call — but nothing is wasted.

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?

The input schema is enormous and deeply nested (line-level facts, chapter 98/99 declarations, agricultural safeguards), yet the description never explains how 'lines' drives the audit or what a coverage-boundary result looks like in practice. There is no output schema, so the brief return-value summary is necessary but thin for a tool of this complexity.

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 only 25% across 4 parameters; mode, as_of, and entry_number have essentially no schema documentation. The description only hints that input is organized 'by entry line' and adds nothing about as_of (which pins the rate version) or entry_number (provenance linkage). It fails to compensate for the coverage gap.

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?

Names a specific verb and resource ('Audit declared duty against supported rates by entry line') and states the output shape (discrepancies, coverage boundaries, provenance). This implicitly distinguishes it from calculate_duty, which computes duty rather than checking a declared figure, though it never names that sibling explicitly.

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 audit scenario (a filed entry with declared duty already present) is implied by 'audit declared duty against supported rates', and the access tier requirement is stated. But there is no explicit when-to-use guidance and no routing to calculate_duty, assess_import_entry, or screen_import_requirements for adjacent tasks.

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