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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the 0-100 scoring scale with 75+ as the blocklist threshold, the fact that verbose pulls in report comments, and a pointer to the web page link. It omits rate limits, auth requirements, and what happens for an unknown or malformed IP.

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, both front-loaded with the highest-value information: what is returned, then how to expand it. No filler, no restatement of the title.

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 field enumeration in the description does the heavy lifting of explaining return values, which is exactly right. The gap is edge-case behavior: not-found IPs, invalid input, and whether results are cached or rate limited are unaddressed.

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 all three parameters are already documented in structured fields, which sets the baseline at 3. The description restates the verbose behavior and adds the meaning of the score threshold, but says nothing about maxAgeInDays (the 30-day default window) that would help an agent reason about result freshness.

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?

States a specific verb+resource ('Reputation of one IPv4 or IPv6 address') and scopes it to a single address, which implicitly separates it from the sibling check_network that handles networks. It goes further by enumerating what reputation data means here (abuse confidence score, reporters, categories, country, ASN, Tor exit), so an agent knows exactly what it gets.

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?

Usage is implied rather than stated: nothing says 'use this for a single IP, use check_network for a CIDR range' or when to prefer get_reports/get_network_report. The only explicit conditional is 'Set verbose to include the latest reports', which is a parameter hint, not a routing rule.

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