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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description is consistent with both. It adds genuinely non-obvious behavior: the category mix is withheld pending a rule rebuild, false positives in open countries were the cause, and the response will contain bucket definitions, null country rows, and a review object whose data date is the layer's window end. That is real disclosure of what the returned payload looks like when degraded.

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 critical fact — 'Under review ... so it is withheld' — is front-loaded, and the return-shape sentence earns its place since there is no output schema. The first sentence does carry a lot of stacked clauses (category mix, source layer, false-positive history, rebuild), more than strictly needed to explain the withholding.

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?

With no output schema, the description compensates by describing the return payload (bucket definitions, null country rows, review object with a data date) and by explaining why the payload is empty. About the only gap an agent might want is an explicit pointer to a working alternative tool while this one is under review.

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% and the single optional country param is documented in-schema with examples (IR, RU, SA). The description only restates the usage ("Pass country=XX for one country") and adds the implication that omitting it returns multiple countries, which is marginal value over the schema.

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 names a specific resource — per-country category mix of nationally blocked domains, sourced from Voidly's national blocklist layer — which distinguishes it from siblings like get_censorship_by_category and get_national_blocklist. It also states plainly that the data is currently withheld, so an agent knows what the tool is for and that it is not producing real content right now.

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?

It gives an explicit calling convention ("Pass country=XX for one country"), implying omission returns all countries, and the 'under review' framing tells the agent not to treat results as substantive. However, it names no alternative for agents that actually need national blocklist data — get_national_blocklist in the sibling list would be the obvious substitute but is never referenced.

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