reports_vat

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

No annotations are provided, so the description must carry the full burden. It does disclose a critical behavior: the requirement for company context (X-Company header/companyId/env var). However, it doesn't state whether this is read-only, what permissions are needed, whether the report has limitations (e.g., currency, tax regime assumptions), or whether it blocks on external data (e.g., ANAF sync). This is a moderate disclosure but incomplete for a report that may feed into tax compliance decisions.

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 a single, information-dense sentence that front-loads the purpose and then enumerates the output contents and the company-context requirement. Efficient with no wasted words, though slightly packed in one long sentence.

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 tool returns a structured report with per-invoice details and multiple summarized figures, and there's no output schema. The description does enumerate what the report returns, which compensates somewhat. However, it doesn't clarify how the per-invoice details are structured, whether results are paginated, or what date semantics apply (calendar month vs. accounting period). For a compliance-relevant reporting tool, more behavioral detail would be valuable, but the description covers the essentials for a simple month-scoped query.

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 schema already documents all three parameters (year, month, companyId). The description adds context by noting companyId overrides the STORNO_COMPANY_ID env var, which maps to the schema's own description. It doesn't add extra meaning about the year/month format or edge cases beyond what schema provides. Baseline 3 is appropriate since schema handles the heavy lifting.

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 clearly states the tool generates a detailed VAT (TVA) report for a month, listing what the report contains (sales, purchases, VAT collected/deductible, net due) and per-invoice details. It's a specific verb+resource+scope, though it doesn't explicitly distinguish from the sibling reports_sales_analysis 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 indicates it requires the X-Company header via companyId param or STORNO_COMPANY_ID env var, which is useful context. However, it doesn't explain when to use this versus other reporting/analysis tools (e.g., reports_sales_analysis, declarations_*, cash_register). The monthly scope is implied but the selection criteria among sibling reporting tools are not addressed.

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