declarations_create

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

With no annotations present, the description carries the full burden and largely delivers: it discloses that VAT/payroll types are auto-populated, that c168 requires attachments as [{name, contentBase64}], that d406 depends on periodType, and that responses return attachments stripped of content ({name, size, mime, stored}). This is rich behavioral context for a mutating create operation.

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 content is highly valuable but presented as one dense paragraph with heavy nested parentheses, making it hard to scan. The core purpose is front-loaded, but the type-by-type detail would benefit from bullet-point structure or a table. No sentences are wasted, but the organization undermines readability.

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 complex 7-parameter tool with 10 enum variants and nested objects, the description covers type semantics, auto-population behavior, input shapes, attachment requirements, and the post-creation workflow. There is no output schema, and return-value details are only partially addressed (via the attachments round-trip note), so it is not perfect, but it is complete enough for an agent to call 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 coverage is 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema: it decodes every enum value into a real-world declaration, explains which types are monthly vs quarterly, and specifies the data.input shape (declaration_form_spec) and the attachment format. This meaningfully extends what the property descriptions alone convey.

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+resource ('Create a new tax declaration') and immediately distinguishes the auto-populated types from the form-based types, giving each of the 10 enum values concrete meaning. An agent can tell exactly what this tool produces and which input path each type follows.

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?

Clearly explains which types are auto-populated from invoices and which require JSON form input, plus the period/month constraints for d301, d398, d406, d212 and c168. The closing workflow hint (declarations_validate → declarations_file_via_agent) routes the agent to the correct follow-up. It stops short of explicitly naming excluded alternatives like declarations_prepare or declarations_upload, but the guidance is strong.

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