sejm-mcp

Treść wypowiedzi ze stenogramu

tresc_wypowiedzi

Read-onlyIdempotent

Treść jednej wypowiedzi ze stenogramu Sejmu jako zwykły tekst, w porcjach po 12 tys. znaków. Wypowiedź prowadzącego obrady („Marszałek”) to często cały dzień, ponad 100 tys. znaków: szukaj w niej parametrem fraza, zamiast czytać porcjami.

Instructions

Input Schema

Name	Required	Description
`od`	No	Od którego znaku zacząć
`data`	Yes	Dzień posiedzenia (RRRR-MM-DD)
`fraza`	No	Szukaj tej frazy w tekście (bez wielkości liter, z polskimi znakami): zamiast porcji zwraca tylko trafienia z kontekstem i ich pozycje (od)
`numer`	Yes	Numer wypowiedzi z wypowiedzi_posiedzenia
`kadencja`	No	Numer kadencji Sejmu; domyślnie 10 (bieżąca, od 13 listopada 2023)
`posiedzenie`	Yes

Output Schema

Name	Required	Description
`uwagi`	No
`zrodla`	Yes
`kalendarz`	No
`wynikCzesciowy`	No	Tylko przy wyniku NIEPEŁNYM: powiedz to użytkownikowi na początku

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.3.1Oct 14, 2026

addedInput schema / properties / fraza

Added value: +{
+  "description": "Szukaj tej frazy w tekście (bez wielkości liter, z polskimi znakami): zamiast porcji zwraca tylko trafienia z kontekstem i ich pozycje (od)",
+  "maxLength": 200,
+  "minLength": 2,
+  "type": "string"
+}

First observedv0.3.0Oct 2, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), yet the description still adds real behavior: output is plain text chunked at 12k characters, and `fraza` switches the response shape to hit-list with context and positions. It does not say what happens when `od` exceeds the speech length.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both load-bearing: the first defines output and chunk size, the second gives the search strategy. No filler, and the core purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

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 documentation is not required. The description covers chunking, the search alternative, and the typical input source (speech number from `wypowiedzi_posiedzenia` via the schema), leaving only edge-case error behavior unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 83%, so the schema does most of the work, but the description adds a concrete usage model: `fraza` returns only matches with context and their `od` positions instead of a chunk, and it explains why the paging parameters matter for very long speeches.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource: returns the plain-text content of a single Sejm transcript speech, delivered in 12k-character chunks. Combined with the `numer` parameter referencing `wypowiedzi_posiedzenia`, an agent can tell this is the retrieval endpoint for a speech listed elsewhere.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises using `fraza` to search long speeches (e.g. the Marshal's full-day remarks exceeding 100k characters) rather than paging through chunks. That is clear mode-selection guidance, but it never states when to reach for this tool versus siblings like `wypowiedzi_posiedzenia`.

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