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

Beyond the annotations, the description discloses meaningful behavioral details: calls are charged even when cached, results are cached for 7 days, cache misses can take up to two and a half minutes, there is a 30-per-hour limit, and the credit is refunded if the provider fails. No contradiction with annotations exists; the readOnlyHint=false aligns with the described non-free, non-idempotent behavior.

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 description is long but densely informative, with each clause covering a distinct operational concern: output contents, normalization, caching, cost, latency, rate limits, and authentication. It is front-loaded with the primary purpose and the most relevant selection-relevant facts, though the output field enumeration could arguably be trimmed.

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?

Given the tool's complexity, the description covers all necessary context: input normalization, caching behavior, costs, failure refund, rate limits, subscription requirements, website_id handling, and the key alternative tool. An output schema is already present, so detailing return values is unnecessary.

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 the schema already documents both parameters. The description adds important semantic clarity by explaining that subdomains and paths are reduced to the registrable domain, and by specifying when website_id is needed, which goes beyond the schema's basic descriptions.

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 states a specific verb and resource: 'Returns the backlink profile of any domain' from the DataForSEO backlinks index, enumerating the exact metrics returned. It explicitly distinguishes itself from the sibling check_domain_rating by naming when that alternative is appropriate.

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?

The description clearly says to use check_domain_rating when only Domain Rating is needed, and explicitly warns not to call check_backlinks twice for the same domain due to credit charges and caching. It also provides rate limits, caching duration, and required subscription context, giving the agent actionable selection criteria.

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