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

Annotations only say the tool is not read-only and not destructive. The description adds substantial behavioral context: declaration checks the file for an AI mark, a found mark keeps the material classified as AI and returns the reason, and listing returns each declaration with its effect (`wirksam`). It also explains returned rights-class values and the `nicht_festgehalten` fallback.

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 dense but front-loaded: purpose first, mode behavior second, return semantics third. Each sentence carries operational information, including the AI-mark check and the rights-class return fields. There is no filler and the length is justified by the dual-mode behavior and lack of output schema.

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?

With no output schema, the description compensates by explaining the return semantics: listing includes each declaration's effect and rights class details. It covers the declaration behavior, listing behavior, AI Act consequence, and the distinction from rights class. Nothing an agent needs in order to choose the correct mode 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. The description still adds meaning beyond the schema by explaining the combined semantics of `asset_key` + `herkunft` versus `project_id` only, and by describing what the declaration check does. The enum values are defined conceptually as human-made versus AI-generated or AI-altered.

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 states a specific resource and verb pair: declare or list where a project's material comes from. It clearly distinguishes the two operating modes (`asset_key` + `herkunft` for declaration, `project_id` only for listing) and explains the EU AI Act Art. 50 consequence. An agent can tell what the tool does without opening the schema.

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 explicit mode-selection rules: use `asset_key` + `herkunft` to declare, use `project_id` only to list. It also states the downstream effect that exports decide AI Act disclosure from this data and that undeclared material counts as AI. The distinction from rights class (`rechte_klasse`) is explicitly called out.

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