get_reference_metadata

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

With no annotations, the description carries the transparency burden. It discloses that coverage varies by provider, that channel status is reported, and that empty vs unanswerable results are distinguishable. It also includes a performance warning for large dataflows. However, it doesn't explicitly state read-only behavior or error handling, though 'get' implies a safe operation.

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 well-structured with an intro, usage note, args list, and returns summary. It is slightly longer than necessary due to the detailed performance example, but every sentence contributes valuable information, so it remains appropriately sized.

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 an output schema exists, the description needn't detail return format, but it still summarizes output (attributes, provenance, channel status) and covers edge cases like provider coverage and empty vs unanswerable results. It omits explicit error scenarios but is otherwise complete for this metadata retrieval tool.

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 fully compensates by explaining each parameter in prose: dataflow_id, key (with performance example), agency_id, and endpoint (with provider examples). This adds substantial meaning beyond the bare schema definitions.

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-resource pair ('Get reference metadata for a dataflow') and lists concrete content types (source, methodology, licence, caveats). It explicitly contrasts with structural metadata ('rather than its structure'), distinguishing it from sibling tools like get_dataflow_structure.

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?

Provides explicit usage context 'Use it to explain or cite data you have retrieved' and a clear when-not distinction ('rather than its structure'). This guides the agent toward appropriate invocation contexts without ambiguity.

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