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

No annotations exist, so the description carries the burden. It does disclose the aggregation granularity ('per month'), the source set (supplier invoices), and the output content (taxable base, input VAT paid), which is meaningful behavioral context. However, it omits relevant traits: it never states the operation is a read-only report, what happens when date bounds are omitted, how currency filtering affects aggregation, or whether unpaid invoices are included.

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?

A single front-loaded sentence that identifies the report, its data source, its output fields, and its regulatory context with no waste. Appropriate sizing for a three-parameter report tool.

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 description partially compensates for the absent output schema by naming the returned metrics (taxable base, input VAT per month). But with all three parameters optional and no annotations, it leaves a real gap: an agent calling with no arguments cannot know the default period or whether currency defaults to all, which the schema's '(default: all)' only covers for currency.

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 100%, so date_from, date_to, and currency are already documented in the schema. The description adds nothing about parameter behavior beyond what the schema provides, so the baseline 3 applies.

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 resource and scope: monthly input VAT (TVA deductibilă) aggregated from supplier invoices, returning taxable base and input VAT. This implicitly separates it from report_vat_collected (output/collected VAT), though no sibling is named 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 phrase 'for decont TVA' implies the use case (Romanian VAT return preparation) and 'supplier invoices' implies the data source, but there is no explicit when-to-use, when-not, or reference to the sibling report_vat_collected. Usage must be inferred from domain vocabulary.

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