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

The annotations already establish that this is a safe, idempotent read, but the description adds substantial behavioral context: the provenance of each mode, the GDPR rationale for limiting data to officeholders, the fact that the register itself contains no named contacts, and the interpretation of empty results. It also tells the agent how results are labeled and that citations are expected, which is far beyond what the annotations convey.

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 purpose and the two-mode distinction are stated first, then the caveats, which gives a good order. The passage is longer than necessary, though: the GDPR justification and the trailing bracketed note about "Ohne KI" add words that do not help the agent invoke the tool correctly.

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?

For a parameter-free, read-only tool with no output schema, the description covers provenance, caveats, empty-result semantics, and citation expectations thoroughly. Minor gaps remain around combining topic with org_name and around result ordering, but nothing essential to a correct call is missing.

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 the baseline is 3, but the description adds real meaning by separating topic/org_name (register lookups) from mdb_name/fraktion (curated evidence database, potentially empty) and by noting that results include Ausgaben. It still does not clarify whether topic and org_name combine with AND or OR, or how limit interacts with the two modes.

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 uses a specific verb-resource pair ("Zeigt Lobbyorganisationen aus dem offiziellen Lobbyregister") and explains that the tool has two query modes: topic/org_name against the register and mdb_name/fraktion against a curated evidence database. That clearly distinguishes the tool from a generic search. However, it never names similar sibling tools (for example, get_eu_lobby_network or search_lobby), so an agent cannot use the definition to choose between them.

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 explicit guidance on which parameter group queries which data source, and it warns that an empty result means no disclosable entry was found rather than that no connection exists. It does not, however, state when to use this tool rather than its EU or general lobby siblings, nor does it cover exclusions, so it stops short of full routing guidance.

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