MCP server that generates SERP-targeted content briefs using DataForSEO and Claude
Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. analyze_serp has a reasonable description (89 chars) and 4 parameters with types and descriptions. generate_brief also has a description (92 chars) but serp_data parameter lacks detail on expected structure. Neither tool documents output schema, making it unclear what fields agents should expect. No error handling guidance. Parameter descriptions lack constraints (e.g., depth range 10-100 is stated but not enforced in schema). Tool names follow verb_noun pattern (positive), but descriptions are minimal for LLM optimization.
Analyze SERP results for a given keyword using DataForSEO API
Generate a SERP-targeted content brief using SERP analysis and Claude
Output schemas not documented. Neither tool specifies what fields agents should expect in responses. analyze_serp returns an 'analysis' object with top_domains, featured_snippets, etc., but this structure is not declared in tool definition. generate_brief output is completely undocumented.
serp_data parameter in generate_brief lacks description of expected structure. Agents cannot infer what fields this object should contain or how to construct it from analyze_serp output.
No error handling guidance. Tool descriptions do not explain what to do if DataForSEO API fails, keyword is invalid, or Claude API times out. Agents receive raw error messages with no recovery path.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 51 | 2026-07-28+ | v2 |
Parameter constraints not enforced in schema. depth parameter states '10-100' in description but schema lacks minValue/maxValue. LLMs may pass invalid values; server-side validation exists but agents receive no guidance on valid ranges.
Tool descriptions are minimal (65-89 chars). Baseline for A+ tools is 194 chars. Current descriptions lack context on WHEN to use each tool, WHAT it returns, and HOW it differs from similar tools. Insufficient for LLM selection reasoning.