isir_stahnout_dokument

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

No annotations are provided, so the description carries the full disclosure burden. It does add a real behavioral trait beyond the schema: the PDF is written into a local cache and the tool returns only metadata (path, page count, text-layer flag), not content. It stops short of covering idempotency or whether a cached copy is reused on repeat calls, which matters for a caching tool.

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 dense sentences with no filler: the first states the action, side effect and return values; the second handles the routing disambiguation. The most decision-relevant information (what you get and what you do not) is front-loaded.

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?

An output schema exists, so the return values need not be re-explained, and the description correctly covers the core behavior. However, with zero annotation coverage and 0% schema description coverage, the unexplained `znovu` parameter leaves a genuine gap an agent cannot resolve from any structured field.

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 0% and the description explains neither parameter. `dokument_id` is inferable from context, but `znovu` (re-download / force refresh) is completely opaque — nothing in the description or schema tells the agent what it toggles or when to set it.

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 names a specific verb and resource (downloads the PDF of a document from ISIR) and states the exact outcome (saved into local cache, returns file path, page count, text-layer flag). It also explicitly distinguishes itself from the sibling that returns text, so an agent can tell the two apart without opening either schema.

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?

It names the concrete alternative for the common confusion case: 'Text nevrací – použijte isir_text_dokumentu' (it does not return text – use isir_text_dokumentu). That gives an explicit routing condition between this tool and the text-extraction sibling, rather than leaving the choice to inference.

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