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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses important behavioral traits: the free-time clock starts at a carrier-defined event, arrival_date is taken as supplied with data_basis='user_supplied_arrival', the response's charge_family field always discloses which charge type answered, and the tool requires payment via x402 returning 402 if unpaid. These contextual details go well beyond annotations and provide no contradiction.

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 description is information-dense yet well-structured: it opens with the core function, then provides usage guidance, alternative mode, payment requirement, and return fields, all in a logical flow. Every sentence adds value—there is no filler or repetition, and the structure makes the content easy to scan.

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 lists the exact return fields (free_days_total, days_elapsed, free_days_remaining, etc.), which fully compensates. It also covers edge cases like storage coverage limitations, payment failures (402), and the data_basis and charge_family fields. For a tool with 8 parameters and several nuanced behaviors, the description is comprehensively complete.

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?

The schema already covers 100% of parameters with descriptions, earning a baseline of 3. The description adds valuable semantics for charge_type—clarifying that 'storage' is a distinct terminal charge, only returned when explicitly requested, with thin coverage and an explicit error listing covered lanes—and explains arrival_date as the clock-starter with user-supplied data basis. This added context justifies a score above baseline, though not every parameter receives additional explanation.

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 uses a specific verb ('report') with a clear resource (free-time countdown) and specifies the required inputs (carrier, country, container type, arrival date). It explicitly distinguishes itself from the sibling tool shippingrates_dd_calculate, which answers a fixed number of days, making this the proactive countdown tool.

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 description directly states when to use the tool ('Use this to answer "how long until this container starts costing demurrage, and how much per day?"') and contrasts it with shippingrates_dd_calculate, noting they share the same engine so numbers agree. It also provides explicit guidance on using charge_type='storage' for terminal storage, with coverage caveats.

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