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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), which 'look up' confirms without contradiction. The description adds genuine value beyond those annotations: the auth requirement ('Needs a free key'), the latency characteristic (sub-5ms), the data source (local dataset), and a concrete result example ('returns US, AS15169'). This is meaningful behavioral context that helps an agent decide to call it and anticipate the response. Minor gap: it doesn't state failure behavior for invalid keys or unsupported input format.

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?

Three short sentences with zero waste: purpose is front-loaded, then the differentiating performance/data-source detail, then the auth requirement and a concrete example. Every sentence earns its place — the example compresses both input format and return shape into a single line. Excellent structure.

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?

For a single-parameter, read-only, low-complexity tool with no output schema, the description carries the return-shape burden well: it lists the returned fields and gives a concrete output example. The auth prerequisite and latency are disclosed. It is slightly incomplete only because it leaves sibling routing (batch/max for broader needs) unaddressed, but for the tool's own scope nothing essential is missing.

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% — the schema already fully documents the single 'ip' parameter as an IPv4/IPv6 address with an example. The description's example ('ip="8.8.8.8" returns US, AS15169') adds a working invocation and expected output, which is marginally valuable, but it does not add new semantic meaning beyond the schema. This matches the baseline 3 for high-coverage schemas.

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 ('Look up an IP address') and enumerates the returned fields (country, continent, ASN, network operator), so an agent immediately knows exactly what this does. It does not explicitly distinguish itself from siblings like asn_lookup or ip_lookup_max; the 'LITE' branding and 'local dataset' hint at the distinction but are not stated. That implicit differentiation keeps it at 4 rather than 5.

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 context is implied rather than explicit: 'Served from our local dataset, sub-5ms' signals a fast lightweight option, and 'Needs a free key' states a prerequisite for calling it. However, the description never names alternatives (ip_lookup_batch, ip_lookup_max, asn_lookup) or states when NOT to use this tool versus them. With 4 siblings available, leaving the routing to inference is a real gap, so this lands at 3.

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