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

Goes meaningfully beyond the readOnly/openWorld/destructive annotations: it states there is no pagination, that no additional provider calls are made, and that unapproved costs block execution (a cost/permission gate). The 'proprietary rankings are not Google ratings or measured traffic' caveat usefully warns about interpreting values.

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?

Short and front-loaded, but telegraphic fragments ('Preserve target kind and provider scope') read as notes to an internal implementer rather than clarifying instructions. No wasted length, though a few phrases earn their place less than others.

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 read-only data fetch with no output schema, the definition should at least characterize what a record contains and how the limit shapes results. It says nothing about return shape or fields, leaving the agent unable to anticipate the payload.

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% and the nested target object (kind enum DOMAIN/PAGE, target string) plus the 1-20 limit are undocumented. 'Preserve target kind' gestures at the kind field but never explains what the modes mean or what the limit bounds; the description does little to close the schema gap.

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?

Identifies the resource as backlink records from a specific index and conveys a bounded/limited nature, but the verb is oblique ('projection') and nothing separates it from siblings like nexscope_seo_backlink_overview, nexscope_seo_domain_backlink_pages, or nexscope_seo_referring_domains. An agent cannot tell from this text which backlink tool returns raw record rows versus aggregates.

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?

'Preserve target kind and provider scope' is a constraint, not a when-to-use rule, and no alternative sibling is named or excluded. With a dozen neighbor backlink tools available, the description gives the agent no routing signal at all.

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