parlament_search_transcripts

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

Annotations already mark readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral detail beyond that: it returns only real spoken contributions (not voting lines), explains that the Language filter deduplicates editions but does not hide French/Italian votes, and states coverage starts at 1999-12-06. These are valuable context for the agent.

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?

The description is structured with distinct sections (main statement, return format, pointer to related tool, use_case, important_notes, example). Every sentence adds value: the limitation of excerpts, the language filter behavior, coverage start, and a concrete example. It is detailed but not bloated, and the front-loaded purpose sentence is immediately clear.

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?

The description covers the essential aspects for a search tool: what it searches, what it returns (short quotable extracts with citation and stable URL), what it does not return (full text), which sibling to use next, scope limitations, and coverage date. It also addresses the Language filter nuance. Given the output schema exists and the input schema has detailed per-parameter descriptions, this is fully complete.

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?

While the description does not individually document each parameter, the input schema itself provides thorough descriptions for all nested properties (limit, offset, council, dates, keyword, session_id, speaker_name, business_number). The tool description adds practical usage meaning via the example (speaker_name='Munz', session_id=5202, keyword='Volksschule') and latency guidance for combining parameters, which goes beyond raw schema listings.

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 opens with a specific verb+resource: 'Wörtliche Wortmeldungen aus den Ratsdebatten durchsuchen (Amtliches Bulletin)' – clearly searching verbatim contributions in council debates. It further distinguishes itself from siblings by stating it returns 'kurze, zitierfähige Auszüge (kein Volltext)' and explicitly redirects to parlament_get_transcript for the full text of a single vote.

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?

The description provides explicit guidance: use this tool for search/snippets, then call parlament_get_transcript for the exact full wording. It also gives a concrete use case and performance tips (combine session_id, business_number, or a date window with a free keyword for best latency), plus notes about synergie with fedlex-mcp.

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