Server has 5 tools with basic schemas and descriptions, but significant gaps prevent production use. All tools have input schemas with type definitions and required fields, which is positive. However, parameter descriptions are minimal or missing entirely (e.g., 'email' in create_contact has no description text, only type). Tool descriptions are present but generic (10-50 chars), below the 50-200 char baseline for LLM optimization. No output schemas documented. Error handling returns raw exception strings rather than actionable recovery guidance. No parameter constraints (enums, ranges, patterns) despite many parameters accepting only specific values (e.g., dealstage should be an enum). Missing idempotency guidance for write operations.

• Expand tool descriptions to 50-200 chars. Example: 'Create a new contact in HubSpot with email, name, phone, and company. Email is required; other fields optional. Returns contact_id for use in get_contact or update_contact.'
• Add descriptions to every parameter. For 'properties' in update_contact, specify: 'Object with HubSpot property names as keys (e.g., {"firstname": "John", "phone": "+1-555-0100"}). See HubSpot docs for valid property names.'
• Document output schemas for each tool. Example for create_contact: 'Returns {"id": string, "email": string}'. This enables LLMs to chain calls correctly.
• Replace free-form strings with enums where applicable. For dealstage, declare: {"type": "string", "enum": ["negotiation", "proposal", "closed_won", "closed_lost"], "description": "Stage of the deal in the pipeline"}.
• Improve error messages with recovery guidance. Instead of 'HubSpot API 400: Invalid email', return 'Invalid email format. Ensure email is a valid address (e.g., [email protected]). If contact exists, try search_contacts first.'

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry