18 tools with consistent naming (verb_noun pattern: list_, get_, create_, delete_). All tools have descriptions (avg ~80 chars, within baseline 34-392). Input schemas present for all tools with proper type declarations. However, descriptions are terse and lack context for LLM selection (e.g., 'List DIDs matching a pattern' doesn't explain when to use vs get_did). Parameter descriptions are minimal (avg ~40 chars vs baseline 72). No output schemas documented. Error handling and recovery guidance absent. Missing tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels. No pagination guidance for list tools despite potential large result sets.

• Add output schema documentation for all tools. For list_dids, document: returns array of {scope, name, did_type, size, created_at, updated_at}. For get_rule, document: {rule_id, scope, name, rse_expression, copies, state, created_at, expires_at}.
• Expand tool descriptions to 80-150 chars with WHEN guidance. E.g., 'List DIDs matching a pattern in a scope. Use this to discover datasets before calling get_did for details. Pattern supports wildcards (*).'
• Add pagination parameters to list_* tools: limit (1-100, default 20), offset (0+). Document in description: 'Returns up to 20 results; use offset to paginate.'
• Add tool annotations via MCP schema: mark create_rule with idempotentHint=false (retries risk duplicates), delete_rule with destructiveHint=true (irreversible).
• Document parameter constraints in descriptions. E.g., did_type: 'One of: FILE, DATASET, CONTAINER. Omit to return all types.' rse_expression: 'RSE expression syntax (e.g., "tier=1&country=US"). Call list_rses first to see available RSEs.'

Inferred effective spec: 2026-07-28+.

• Relies on Dynamic Client Registration (deprecated) - use Client ID Metadata Documents (CIMD)