Three well-named, read-only tools with clear descriptions and complete input schemas. All tools follow verb_noun naming (search_, query_, layer_info). Descriptions are concise (100 - 180 chars) and explain WHAT, WHEN, and WHAT-TO-DO-NEXT. Input schemas include types and descriptions for all parameters. However, output schemas are NOT documented, LLMs cannot predict response structure or plan downstream calls. Parameter descriptions lack format constraints (e.g., 'url must be https and end in /FeatureServer/<n>' is stated in code but not in schema description). No error handling guidance in descriptions. No pagination metadata documented for search_datasets despite returning a 'total' field.

• Document output schemas for all three tools. For search_datasets, specify: { total: number | null, count: number, datasets: Array<{ id, name, summary, org, org_id, record_count, type, url }> }. For query_layer and layer_info, reference ArcGIS REST API response structure or provide a sample.
• Add format constraints to 'url' parameter descriptions: 'Must be https, public ArcGIS host (no IPs or localhost), and end in /FeatureServer/<n> or /MapServer/<n>. Example: https://services.arcgis.com/org/rest/services/MyService/FeatureServer/0'.
• Add error recovery hints to query_layer and layer_info descriptions. E.g., 'If the query fails with a 400 error, check the where clause syntax (SQL-like). If 403, the layer may require authentication.'
• Document pagination in search_datasets response: 'Returns up to limit datasets. If total > count, use offset parameter in a follow-up call to fetch the next page.'
• Add a note to query_layer description: 'Large result sets (>500 features) may exceed LLM context limits. Use limit and where clauses to narrow results. Geometry is included by default; use out_fields to exclude it if not needed.'