declaration_form_spec

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low and the description correctly doesn't restate it. It adds genuine value by disclosing the scope and depth of the payload, including that it surfaces web-form rules the DUK validator misses (citing rule IDs BR-C168-00991/0041/005911), which tells the agent this is authoritative reference material rather than a summary.

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?

Front-loaded with the main claim, then a dense but purposeful enumeration of what the spec contains, followed by two short action sentences. The single long sentence is packed but every clause carries distinct information; nothing is filler.

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?

There is no output schema, so the description bears the burden of describing the return, and it does enumerate the constituents well (schema, XML mapping, business rules, filing steps, example). It could go further on size/structure of the returned document, but for a reference-lookup tool an agent has enough to call it correctly.

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% and both parameters (type, xsd) are already documented in the schema. The description adds no parameter-level detail — notably it never explains the xsd=true branch that switches the return to the raw ANAF XSD, leaving that entirely to the schema.

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?

States a specific verb and resource: it returns the complete specification needed to fill an ANAF declaration form. It enumerates the concrete payload (JSON input schema, XSD attribute mapping, business rules, filing steps, example) and names the target consumer (declaration_build), so it is unmistakable against siblings like declaration_forms or declaration_form_versions.

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?

Explicit ordering instruction: 'Read it before declaration_build.' It also states a prerequisite for C168 addresses (codes must come from anaf_nomenclator_*) and a prohibition (never invent CNPs or CUIs), naming the sibling tools to use instead.

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