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

With no annotations, the description carries the full burden and does reasonably well: it discloses the pagination contract via next_offset, the conditional extra vote_result payload for polls (with its enum-like value set), and the returned content categories. It does not state permission requirements or read-only guarantees, but as a read-style retrieval tool there is little destructive behavior to warn about.

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?

Three tight sentences, front-loaded with what the tool returns, followed by the paging rule and the poll special case. No filler, though the poll clause is fairly dense and the sentence boundaries could be cleaner.

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 three-parameter read tool with an output schema present, the description covers the essentials: content shape, paging, and the poll-specific return behaviour. The only real hole is max_chars, which the agent must guess from the schema default alone.

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 description coverage is 0% for all three parameters, so the description must compensate. It explains offset well (start of the excerpt, continue with next_offset) and doc_id is self-evident from the name, but max_chars is never mentioned in the description despite having a non-obvious default of 6000.

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 names a specific verb and resource and enumerates exactly what is returned: metadata, a text excerpt, linked actors, topics and relations. It implicitly separates itself from siblings like get_vorgang or get_relations by listing its own payload, but it never names an alternative, so it stops short of the top band.

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?

It gives concrete continuation guidance ('Weiterlesen mit offset = next_offset') and a conditional branch for source_type poll, which is genuine usage help. However there is no guidance on when to pick this tool over search, verify_quote or get_vorgang, which is the main selection decision an agent faces.

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