Szukaj druków sejmowych

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the bar is lower. The description adds useful operational context beyond that: the result is capped at roughly 20k characters and the remainder is retrieved via paging, and that with dates only the count of additional prints is returned unless dodatkowe=true. This is genuine behavioral detail not present in the annotations.

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?

One dense but front-loaded block: purpose and scope lead, then filtering nuances, then pagination, then sibling routing. Every clause carries information, though the middle section is fairly packed and could be split for scannability.

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?

With annotations covering the safety profile and an output schema present, the description need not explain return values, and it correctly focuses on filter semantics and routing. It covers the non-obvious behaviors (inclusive dates, additional-print handling, result-size paging) so an agent can call it 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 a baseline of 3 already applies, but the description goes further by explaining semantics the schema only labels: the doreczenia-vs-dokumentu date choice (including that it drives the 'week's prints' interpretation) and the number-phrase matching behavior of fraza. This meaningfully enriches what the enum and patterns 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 and resource up front: searching parliamentary prints of a term by title words and date, enumerating the content types (projekty, sprawozdania, opinie, autopoprawki, informacje) and the sort order (od najnowszych). It also routes to siblings at the end (druk for details, proces for the legislative path), so an agent can distinguish it from szukaj_projektow or szukaj_pism.

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 conditional guidance: dates are inclusive and default to delivery date ('doreczenia') while 'dokumentu' filters by drafting date; phrases with a print number (e.g. "autopoprawka 2865") surface related prints; additional prints are counted via razemDodatkowych or listed with dodatkowe=true. It names sibling tools for follow-up (druk, proces), though it does not frame explicit when-not-to-use conditions versus those siblings.

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