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

Annotations already cover readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds meaningful context: the knowledge base is curated, continuously updated, has 4,000+ principles with confidence scores and source tracing, and Pro/Enterprise tiers return additional fields (full_text, source). This goes beyond annotations to clarify 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 well-structured with INPUT, RETURNS, and USE WHEN sections. Each sentence conveys essential information: knowledge base characteristics, parameter constraints, output format, and usage context. No filler or repetition.

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 has 4 parameters, an output schema, and rich annotations, the description is complete: it explains what the knowledge base is, input constraints, return fields with tier differences, and when to use it. It leaves little ambiguity for an agent deciding whether to invoke this 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 100% with detailed parameter descriptions for query, top_k, category, and min_confidence. The description summarizes these, including the same min_confidence advice already in the schema ('Default 0.5 filters noise; raise to 0.8+ for high-confidence claims only'). It adds the semantic-search framing but no new parameter-level meaning.

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 opens with 'Semantic search over the Proximens GEO Engine', a specific verb+resource pair that clearly identifies the operation. It uniquely positions this tool against siblings like proximens_geo_audit_url or proximens_geo_get_principle by emphasizing search over a structured knowledge base of GEO principles.

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 'USE WHEN' clause provides explicit guidance: 'when you need evidence-backed answers about how AI search engines (ChatGPT, Perplexity, Gemini, Google AI Overviews, Copilot) select, rank and cite web content.' This clearly separates it from audit/compare tools, though it does not explicitly name alternative tools or list when not to use.

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