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

No annotations are supplied, so the description carries the full behavioral burden. It does real work by disclosing the underlying source (IMF PortWatch satellite ship tracking), the cadence (weekly), and the aggregation windows (4-week and 13-week y/y, latest month y/y). It says nothing about read-only semantics, rate limits, latency, or what happens when an economy is uncovered — gaps that matter given zero annotation coverage.

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?

The content is dense and nearly waste-free, and it is front-loaded with the product name. However, it is delivered as one sprawling run-on sentence that stacks freight modes, economies, cargo classes, and aggregation windows, making it hard to parse and putting the actionable parameter guidance last.

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, the description must convey the return shape, and it does so thoroughly — granularity, cargo-class breakdown, geographic coverage, and y/y windows are all spelled out. What remains unclear is the response's actual structure (how freight-mode lanes versus seaborne volumes are organized) and how the summary-versus-history distinction manifests in the payload.

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%, with both 'weeks' and 'economy' documented in the schema itself, so the baseline is 3. The description adds modest value by clarifying that omitting economy yields a summary of all economies while specifying one returns that economy's weekly history — a distinction the schema's 'omit for all' only partially conveys. It adds nothing about valid economy codes or the relationship between 'weeks' and the returned series.

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 a specific product ('Global Trade Nowcast') and enumerates the resource's contents precisely: freight volumes by mode (rail, road, air, land border) and weekly seaborne trade volumes with cargo-class splits. An agent knows exactly what data domain this returns. It stops short of differentiating from the sibling 'get_nowcast', which a reader could reasonably confuse with it.

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 closing line 'Omit economy for a summary of all; give one for its weekly history' tells the agent how to choose a parameter value, which implies the two usage modes. But there is no explicit statement of when to reach for this tool versus get_nowcast, get_weekly_pulse, or get_aggregate, and no exclusions or prerequisites are given.

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