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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful context beyond that — 5 credits per page, API key required, relation strength values, and the caveat that 'a relation is a link, not proof of common ownership' — but says nothing about result ordering or how verdicts are surfaced.

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?

Front-loaded with the core question, then the pivot list, then the caveats and cost. Every clause adds information — 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 an output schema present, return shape need not be explained, and annotations cover read-only behavior. Cost, auth, and interpretation caveats are all supplied; the only real gap is pagination semantics for the page/per_page parameters.

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 0%, so the description carries the burden for all three parameters. It hints that results are paginated ('5 credits a page') but never explains page numbering or the per_page cap of 50, leaving two of three parameters undocumented in both the schema and the text.

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 and resource ('Which other domains share infrastructure or a kit with this one') and enumerates the exact pivots used (IP, /24, ASN, name servers, certificate, registrar, template, tracking id). That level of specificity clearly separates it from lookup_domain, which examines a single domain.

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 states the condition that selects this tool (you want domains linked by shared infrastructure) and an explicit scope exclusion ('CDNs and shared hosting are not pivoted on'). It stops short of naming lookup_domain or another sibling as the alternative when the agent only wants single-domain data.

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