declarations_upload

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false), the description adds real behavioral context: type/year/month are derived from the document rather than supplied, the uploaded file is what gets validated and filed, and the recipisa is stored in the dosar. It does not address duplicate uploads or what the call itself returns, which is the main remaining gap for a non-idempotent write.

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 action and accepted formats, followed by downstream consequences. Every sentence adds information, though the second sentence packs several ideas into one long em-dash construction and could be split for 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 two-parameter import tool with no output schema, the description covers format acceptance, metadata derivation, and the validate/file follow-up chain. The only shortfall is that it doesn't say what the upload call itself returns (declaration id? parse errors?) before handing off to declarations_validate.

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 filePath and companyId are already documented. The description reinforces the file semantics by naming the accepted formats, but says nothing about companyId or the env-var override. Baseline 3 is appropriate when the schema carries the parameter burden.

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?

Specific verb (bring/upload) plus resource (a declaration produced elsewhere) and the exact accepted formats (XML, ANAF PDF from SAGA/DUKIntegrator/filled ANAF form). This clearly separates it from declarations_create or declaration_build, which generate declarations rather than importing them.

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 establishes the context of use — documents produced in another program — and explicitly says nothing is regenerated, which steers agents away from build/create siblings. It stops short of naming the alternative tool or stating exclusions (e.g. when to use declaration_build instead), so it's clear but not a full when/when-not map.

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