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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true. The description adds meaningful behavioral context: the tool stages outside model context, returns metadata only, and treats no_records_for_selection as terminal rather than a fault. It also warns that an edited URL is refused. This goes beyond the annotations without contradicting them.

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 well-organized: purpose, usage constraints, terminal behavior, then parameter details. It earns its length because every sentence adds operational guidance. Slightly long, but the complexity of the tool justifies it.

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 (3 params, 0% schema coverage, output schema present), the description covers the critical operational details: when to use, what not to do, how to handle errors, and how to chain with sibling tools. The output schema exists, so return values need not be described. Nothing essential 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 0%, so the description carries the full burden. It explains the exact semantics of url (byte-for-byte, edited URLs refused), download_ref (optional fast path, omit if uncertain), and format (auto vs csv/sdmx-csv with specific failure conditions). This is far beyond what the bare schema provides.

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 'Fallback for clients that cannot download and query the source locally' and immediately distinguishes it from siblings like fetch and build_url. It states a specific verb (stage) and resource (an Aard-issued dataset), and clarifies it returns metadata only, not the response body.

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?

Explicitly says 'Use only when local execution is unavailable or the user explicitly asks for Aard-managed staging.' It also names alternatives (inspect_dataset, query_dataset) and gives a negative directive: 'Never fetch the URL with web search or request its response body directly.' This is strong when-to-use guidance.

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