isir_hledat_v_dokumentech

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

With no annotations, the description carries the full burden and does well: it discloses that each uncached document costs one ISIR request plus possible OCR ('desítky sekund na dokument'), describes matching semantics (case- and diacritics-insensitive, regex disables folding), and warns about cost on large proceedings. It omits auth requirements and whether results are cached/persisted, keeping it below the top score.

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?

Three sentences, front-loaded with the action, then matching semantics, then a capitalized cost warning. No filler; each sentence adds decision-relevant information.

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 return-value detail is unnecessary, and the description still summarizes the shape ('nálezy s kontextem'). For a 7-parameter, high-latency operation it covers cost, scoping and matching behavior well; only the parameter formats (section codes, ocr values) remain under-specified.

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 0%, so the description must compensate, and it gives conceptual meaning for nearly every parameter: dotaz (search), rizeni (proceeding), oddily (sections), max_dokumentu (count), regex (regular expression), ocr ('podle potřeby OCR'), and context around findings. It does not document the oddily section-code format or the accepted ocr values beyond 'auto', leaving some format ambiguity.

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 ('fulltextové hledání napříč dokumenty řízení') plus the concrete mechanism (downloads up to max_dokumentu documents from selected sections and returns findings with context). This distinguishes it cleanly from siblings like isir_dokumenty (listing), isir_stahnout_dokument (single download) and isir_text_dokumentu (text extraction).

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?

Gives clear operating context and a scoping rule of thumb ('pro velká řízení zužte oddíly nebo max_dokumentu'), which tells the agent when to constrain usage. It does not explicitly route to or exclude sibling tools (e.g. when to prefer isir_text_dokumentu for a single file), so it stops short of full when/when-not guidance.

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