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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses key behaviors: filters outside a collection's set are rejected locally, query wildcards are trailing-only, council minutes and ministerial decrees have PDF-only surfaces via document_url, and some collections are 'authentic' while others are not. This adds substantial operational context that an agent needs to call the tool correctly, with no contradiction to 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?

The description is long (due to the 7-collection matrix) but densely packed and well-structured with semicolons and parentheticals. It front-loads the primary purpose and collection list before diving into filter applicability. A few sentences could be trimmed (e.g., repeating authentic status), but nothing is wasted.

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?

Given the tool's complexity (23 parameters, 7 collections, output schema present), the description is comprehensive. It explains what each result carries, points to ris_list_reference for the detailed per-collection matrix and issuer lists, and clarifies the local rejection of unsupported filters. The output schema exists, so return-value details are not needed. An agent has everything required to select the right collection and filters.

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?

Even though the schema covers 100% of parameters with descriptions, the tool description adds critical cross-parameter meaning: it maps each filter to the collections that support it (e.g., 'number applies to social_insurance, veterinary, health_structure_plans'), explains abbreviation expansion for issuers, and clarifies that ministerial_decrees date by force rather than publication. This goes well beyond the isolated per-parameter schema descriptions.

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 clear verb+resource statement ('Search Austria’s sectoral official gazettes and executive documents'), explicitly enumerates all seven collections, and distinguishes itself from sibling search tools by its domain-specific scope and by naming ris_list_reference for supplementary reference data. It leaves no ambiguity about what this tool is for.

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 gives clear context on when to use this tool (announcements/gazettes) and even points to ris_track_changes for exact recency windows and ris_list_reference for per-collection filter details. It does not explicitly list all sibling alternatives (e.g., 'use ris_search_legislation for legislative acts'), but the tool name and collection listing make the intended scope obvious. Slight deduction for not explicitly stating exclusions.

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