Three well-named, read-only tools with clear descriptions and complete input schemas. Tool names follow verb_noun pattern (search_datasets, query_layer, layer_info). Descriptions are substantive (150 - 200 chars) and explain what each tool does and when to use it. All required parameters are marked. However, output schemas are not documented, LLMs cannot predict response structure. Parameter descriptions lack format constraints (e.g., 'url must be https and end in /FeatureServer/<n>' is in code validation, not schema). No error handling guidance in descriptions. Missing pagination documentation for search_datasets despite returning a 'total' field.

• Document output schemas for all three tools. Add a 'Returns' section to each description or create a separate schema document. Example: 'Returns {total: number, count: number, datasets: [{id, name, summary, org, org_id, record_count, type, url}]}'.
• Move URL validation rules from code into parameter descriptions. Change query_layer.url description to: 'Feature/Map Service layer url (https only, public ArcGIS host, must end in /FeatureServer/<n> or /MapServer/<n>).'
• Add pagination guidance to search_datasets description: 'Returns up to `limit` datasets. If total > count, use page[size] query parameter in subsequent calls to iterate. Default limit is 20.'
• Add error recovery hints to query_layer and layer_info descriptions. E.g., 'If query fails, verify url with layer_info first and check where clause syntax against ArcGIS SQL-92 spec.'
• Specify SQL format constraints in query_layer.where description: 'ArcGIS SQL-92 syntax; use single quotes for string literals, double quotes for field names. Example: "STATE = \'CA\' AND YEAR >= 2020"'.