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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses a real behavioral trait: the underlying source conflates CensoredPlanet rows and IODA outages with blocks, so the tool returns null rows plus a review object with verdict 'unknown' and no data date. That tells the agent exactly what a call will yield and why — high-value context that annotations do not carry.

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?

Two sentences, no padding, but the ordering is inverted: a long run-on caveat comes before any statement of what the tool does. Leading with the review status rather than the function forces the agent to parse the warning to recover the purpose.

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 correctly takes on the burden of describing the return value (null rows plus a review object with verdict unknown), which is precisely what an agent needs before calling an effectively dead endpoint. The remaining gap is that it does not point to a working alternative for the same question.

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 100%, so both parameters are already documented in the schema, including the ASN format example and ISO country codes. The description's parenthetical 'optional asn for one network' merely restates the schema, so the baseline 3 applies.

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 phrase 'per-network category block rates' does identify the resource more precisely than the tool name, but there is no verb and the statement is buried inside a data-quality caveat. An agent must infer that the tool returns an ISP/ASN-level category blocking profile per country, and nothing distinguishes it from siblings like get_isp_risk_index or get_censorship_by_category.

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?

'Pass country=XX (optional asn for one network)' gives invocation guidance for both parameters. However, there is no explicit when-to-use vs. when-not, and critically no routing to an alternative even though the description itself says the tool currently produces no usable output.

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