Audit a domain's backlink profile: health score, risk flags, link quality breakdown, anchor text profile, top and risky backlinks, and outbound link summary. Scores are derived from a sample of the 250 most recent backlinks, not the full profile.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds significant behavioral context beyond annotations by disclosing that scores are derived from a sample of the 250 most recent backlinks, not the full profile. This is a critical limitation that affects interpretation of results. No contradiction with annotations.
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 two sentences: the first lists the tool's outputs, the second provides the crucial sampling caveat. Every word earns its place, no fluff or repetition. It is well-structured and immediately highlights the key limitation.
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 no output schema, the description takes on the burden of explaining return content, which it does thoroughly by listing health score, risk flags, link quality breakdown, anchor text profile, top and risky backlinks, and outbound link summary. The sampling caveat adds essential context for interpreting results. For a read-only tool with one input, the description is complete enough for an agent to invoke it correctly.
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 has only one parameter 'domain' with a basic type of string and no description (0% coverage). The description compensates by starting with 'Audit a domain's backlink profile', making it clear the domain parameter is the target of the audit. It doesn't add format details (e.g., bare domain vs URL), but with a single parameter, the meaning is adequately conveyed.
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 uses the specific verb 'Audit' and clearly identifies the resource ('a domain's backlink profile'), then enumerates the exact components included: health score, risk flags, link quality breakdown, anchor text profile, top and risky backlinks, and outbound link summary. This level of specificity distinguishes it from sibling tools like get_backlinks or get_link_velocity.
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 implies when to use the tool—when a comprehensive backlink audit is needed rather than just a list of backlinks. It doesn't explicitly name alternatives or exclusion criteria, but the phrase 'Audit a domain's backlink profile' gives clear context. The sampling caveat also helps set expectations for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The tool set is largely well-disambiguated with clear prefixes (get_, outreach_, zeekeo_) and detailed descriptions for each tool. Some tools like get_site_explorer and get_site_health could be confused at a glance, but their descriptions clearly separate their purposes. Overall, the naming and descriptions prevent meaningful ambiguity.
All tools follow a consistent get_ prefix for data retrieval, with sub-prefixes like get_gsc_, get_page_, and outreach_/zeekeo_ for distinct workflows. There is no mixing of naming conventions (e.g., camelCase) or inconsistent verb usage. The naming pattern is uniform and predictable.
With 63 tools, this server vastly exceeds the typical 3-15 tool scope, categorizing as an extreme overflow. Even for a comprehensive SEO and outreach suite, the sheer number is overwhelming and likely includes redundant or overlapping functionality. This would be confusing for agents and users alike.
The tool set covers a wide range of SEO, backlink analysis, Google Search Console data, and outreach workflows, appearing nearly complete for its stated purpose. However, several tools are marked as 'v1 stub' (e.g., get_internal_links, get_schema_markup), indicating incomplete functionality. Despite these gaps, the overall coverage is extensive and well-rounded.
