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

The description presents this purely as a read-only report but the annotations declare readOnlyHint=false and destructiveHint=true, an inconsistency an agent could act on. The description does add genuinely useful behavior beyond the annotations, namely that the call consumes SEO add-on credits and requires the add-on, which is real value but does not resolve the conflict.

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 report's identity and contents, then jobs, then sorting and filter semantics, then cost. Dense but every clause carries information; the uppercase emphasis on DETECT NEGATIVE SEO is slightly noisy but functional.

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 details are appropriately omitted, and the description covers purpose, use cases, sort/filter semantics, and credit cost. What remains thin is the meaning of target (domain vs URL) and limit/refresh behavior, a minor gap for a reporting tool.

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 0%, so the description carries the burden and does well: it enumerates order_by values, defines status_type (live/all/lost), and explains min_spam_score (0 = off). It leaves limit, refresh, and the accepted format of target unexplained, so it compensates for most but not all of the 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?

States a specific verb+resource ('Anchor text report') and immediately defines the exact output grain: every anchor text pointing at a domain, with referring-domain count, spam score, and nofollow counts. That grain clearly separates it from seo_backlinks, seo_backlink_list, and seo_referring_networks.

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?

Explicitly names the two jobs (brand wording discovery, negative-SEO detection) and prescribes sorting per goal ('referring_domains' for attack detection, 'backlinks' for volume, 'spam_score' for worst-first). No sibling alternative is named by name, so it stops just short of the top score.

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