declarations_create

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does reveal key behaviors: the tool auto-populates from invoice data, aggregates by CIF and VAT rate, and supports specific declaration types. However, it does not disclose whether creation overwrites existing declarations for the same period, whether companyId is required or optional, what role ANAF validation/sync plays during creation, or the exact return value/outcome when successful.

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?

Two sentences, front-loaded with the core action and purpose. The first sentence establishes verb, resource, and behavior; the second adds supported types and aggregation logic. No wasted words. Minor deduction because it could be tightened by folding the type list into the schema reference since the input schema already enumerates the enum values.

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?

For a creation tool with 5 params (3 required), no output schema, and no annotations, the description does a reasonable job: it explains the creation behavior, supported types, and aggregation logic. However, it does not address whether a duplicate declaration for the same type/year/month is permitted, whether prior declarations must exist (dependencies), or what the response contains. Given the complexity of this domain (tax declarations with ANAF interactions) this is a moderate gap but not severe.

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 the structural baseline is 3. The description adds genuine value beyond the schema by explaining how 'type' relates to tax declaration forms, how the period (year/month) drives the aggregation window, and that companyId overrides the STORNO_COMPANY_ID env var (already in schema). The aggregation-by-CIF-and-VAT-rate detail clarifies the semantics of the period parameters. Minor deduction because periodType's meaning ('monthly' vs alternatives) is not elaborated, and the type enum values (d394, d300, etc.) are listed without explaining which form each represents.

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 'Create a new tax declaration and auto-populate it from existing invoice data' — a specific verb (create) plus resource (tax declaration) plus behavior (auto-populate). It enumerates supported types and explains the aggregation logic by partner CIF and VAT rate. This distinguishes it from sibling declaration tools like declarations_submit, declarations_recalculate, and declarations_prepare.

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 explains what happens during creation (auto-population from invoices, aggregation by CIF/VAT rate for the specified period) which gives implied context about when to use it. However, it doesn't explicitly state when NOT to use this tool versus alternatives like declarations_prepare, declarations_recalculate, or how this differs from declarations_sync. The context is clear but exclusions and alternatives are not stated.

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