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

Annotations indicate readOnlyHint=true, consistent with description. The description adds important behavioral details: edition-awareness (text for the resolved edition only), possibility of null text for historical editions, and combined decision retrieval with with_decisions. No contradictions.

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?

Information is packed in one paragraph with clear front-loading of purpose. Every sentence adds value, though a more structured layout (e.g., bullet points) could improve readability. Still concise and efficient.

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 5 parameters (one undocumented), no output schema, and moderate complexity, the description covers main functionality but lacks full return value structure and explanation of the instanser parameter. Partial completeness limits agent understanding.

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 0%, so description carries the burden. It explains lov, section, on_date, and with_decisions meaningfully, including examples and behavior. However, the instanser parameter is not described, leaving a gap.

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 clearly states the tool retrieves text for a law section with a concrete example (lov='straffeloven', section='257'). It distinguishes from siblings like get_law (whole law) and find_decisions_applying_law (decision search) by focusing on a specific section and optionally including decisions.

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 context on when to use on_date for edition disambiguation and how to specify law using ID or short title. It mentions with_decisions as a combined alternative to separate tool calls. However, it does not explicitly state when not to use this tool or compare with all siblings.

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