fawtar_vat_summaryOutput VAT charged on sales, input VAT paid on expenses, and the net payable for a date range — the figures a VAT return is built from. Recoverable input VAT only; expenses marked non-recoverable are excluded, as they must be.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | YYYY-MM-DD, inclusive. | |
| from | Yes | YYYY-MM-DD, inclusive. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and non-destructive. The description adds meaningful behavior beyond that: it discloses that only recoverable input VAT is included and explicitly excludes non-recoverable expenses. This is useful domain-specific behavior not visible in the schema.
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 well-front-loaded sentence that states the core outputs first, then adds the important exclusion rule. It contains only relevant information and no redundant elaboration.
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?
Despite having no output schema, the description fully enumerates the returned figures and the exclusion behavior. The two date parameters are already documented in the schema, and the read-only safety is covered by annotations. Nothing essential is missing.
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%, with from and to both documented as inclusive YYYY-MM-DD strings. The description only refers to a 'date range' and adds no extra parameter-level detail, so the baseline of 3 is appropriate.
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 precise resource ('VAT for a period') and the exact figures computed: output VAT on sales, input VAT on expenses, and net payable. This clearly separates it from sibling tools like list or get by specifying the summary nature of the result.
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 gives clear context: it is for a date range and provides the figures a VAT return is built from. It doesn't explicitly mention when not to use it or name an alternative tool, but the purpose is specific enough that an agent can infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
fawtar_create and fawtar_create_invoice are clearly separated by the explicit warning that invoices need the specialized tool, and get/list/outstanding/vat_summary each have distinct read/report purposes. The only mild ambiguity is fawtar_outstanding overlapping fawtar_list with filters, but descriptions make the specialized intent obvious.
All tools share the fawtar_ prefix and snake_case, but the action suffix is inconsistent: create/get/list are generic verbs, create_invoice combines verb+noun, and outstanding/vat_summary are noun-phrase report names rather than verb_noun commands.
Six tools is a compact, well-scoped set for a broad API: three generic CRUD-ish verbs and three specialized financial actions (invoice creation, outstanding report, VAT summary). Each tool has a distinct role and the count feels intentional.
The surface covers creation, retrieval, listing, and key financial reports, but there are no update/delete tools for editable master data and no way to create credit notes or debit notes even though the invoice tool explicitly directs corrections to credit notes. These are significant gaps that will make common workflows fail.