Server has 4 tools with clear naming (verb_noun pattern) and reasonable descriptions (100-200 chars). All tools have input schemas with type definitions and parameter descriptions. However, output schemas are not documented, responses are raw JSON strings without structured field definitions. Error handling is basic (throws errors but lacks recovery guidance). The deprecated set_token tool adds maintenance burden. No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels. Parameter validation is present but descriptions could be more explicit about constraints.

• Document output schemas for all tools. Define the structure of jobId responses, enrichment results, and status fields so LLMs know what to expect and can chain calls.
• Remove the deprecated set_token tool entirely or migrate all clients to set_auth_token. Maintaining two identical handlers increases confusion and maintenance cost.
• Add tool annotations: mark set_auth_token and set_token with destructiveHint=true (modifies session state); mark submit_lookup and check_lookup with readOnlyHint=true.
• Enhance error messages with recovery guidance. E.g., 'No auth token configured. Call set_auth_token first, or set YOURICP_AUTH_TOKEN environment variable.' instead of bare error.
• Add explicit constraints to parameter descriptions: 'emails: array of valid email addresses (max 100 per call)', 'linkedin_urls: array of valid LinkedIn profile URLs (max 50 per call)'.