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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds the crucial behavior that the output is a mere draft with no external side effect ('NIKAM neodesila') and that sending is out-of-band, which is exactly the kind of disclosure annotations cannot convey.

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 tight sentences with the core action front-loaded and the no-send constraint placed immediately after. No wasted framing, though the capitalization of 'NAVRH' and 'NIKAM' is stylistic noise.

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 4-required-param generator with no output schema, the description covers what is produced and its lifecycle. It does not describe the returned artifact format (file/id/location) or whether regeneration overwrites a prior draft, which are minor gaps.

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%, including enum descriptions for submissionType, so the schema already carries the parameter meaning. The description's gloss of priznani/kontrolni matches the enum docs and adds no new format or constraint detail.

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 (vygeneruje) and resource (navrh XML podani DPH) and scopes it to a month with two concrete variants (priznani / kontrolni hlaseni). It is clearly distinguishable from sibling read tools like list_vat_filings or get_vat_summary.

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?

Makes the usage context clear: this only prepares and stores a draft, while actual submission happens in the dashboard after user review. It does not name sibling alternatives (e.g. list_vat_filings for reading existing filings), so it stops short of explicit routing.

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