Publications and reports

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

Adds substantial context beyond the readOnly/idempotent annotations: files are binary and not read here, the agent should hand links to the user, the newest economic_trends/monetary_reports issue carries file links while others carry their own `url`, and publications lag their period so the newest issue can be stale.

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?

Core purpose is front-loaded in one sentence, followed by a compact kind-by-kind enumeration. Dense but each sentence carries operational information; the kind list is near the length limit without waste.

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?

No output schema exists, and the description covers what is returned (issue list, file links, `url` field, ordering) plus the freshness caveat, which is exactly what an agent needs to call it and report results correctly.

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 enum is already documented, but the description adds value by explaining what each kind actually contains (balance sheets, money and credit; rial interbank market and OMO) and file formats per kind. It does not clarify `limit` beyond the schema, keeping it below 5.

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?

Opens with a specific verb+resource ('List the newest Central Bank publications of one kind with download links'), including ordering ('newest first'), which immediately separates it from siblings like cb_statistics or cb_news.

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?

Enumerates each of the four kinds with what they contain and periodicity, and explicitly routes the agent elsewhere when it needs the numbers ('To read the numbers of the monthly Excel files use cb_statistics'). This is an explicit alternative selection, not inference.

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