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

Annotations already declare readOnlyHint=false and destructiveHint=true, but the description goes far beyond that: it specifies that it WRITES, stores a task, sends plot geometry and HS code to an external service, does NOT forward operator/supplier identity, returns a task handle, files nothing with any authority, costs 5 credits, and auto-refunds on failure. This level of behavioral disclosure is exceptional and fully informs the agent of side effects, privacy, and cost implications.

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 a single dense paragraph but every sentence earns its place: it covers the core action, side effects, privacy, workflow (confirm first), cost, and alternative tool. It is front-loaded with the primary action and avoids extraneous detail. Slightly long for a tool description, but given the complexity and the amount of critical information, it remains appropriately concise.

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 (nested objects, external service call, side effects, cost, and expected follow-up), the description covers all essential context: what happens, what isn't forwarded, how to retrieve the result, the need for user confirmation, the cost and refund policy, and the fact that it doesn't file with authorities. The output schema is present, so the return format is already defined; the description does not need to repeat that. Nothing an agent needs to call it correctly 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 description coverage is low (20%), so the description is expected to compensate. It does mention that 'operator and supplier details' are passed and that 'plot geometry, HS code, country and quantity' are sent upstream, which clarifies the role of several parameters. However, it does not explain all parameters (e.g., producer, role enum, harvest_window format) and leaves many nested fields undocumented. The description adds value but not enough to fully offset the schema gaps.

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 specific verb and resource: 'Compile and sign an Annex II Due Diligence Statement.' It then clarifies the exact side effects (stores a compile task, sends data to emem.dev) and distinguishes itself from the read sibling eudr_get_dds by explicitly naming it as the tool to fetch the outcome. The purpose is unambiguous and distinct from all 15 sibling tools.

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 clear when-to-use guidance: it tells the agent to confirm details with the user first, explains that the tool costs credits (unlike all others), and directs the agent to eudr_get_dds for reading the result. It does not explicitly state when NOT to use it, but the context of the workflow (preparing a DDS) sufficiently implies when it is appropriate, and the alternative is named.

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