Two tools with complete input/output schemas and reasonable descriptions. Naming follows verb_noun convention (web_search, web_fetch). Descriptions are adequate (100-150 chars) but lack actionable guidance on when to use each tool or how they differ. Parameters are typed and mostly described, but lack constraints (enums, ranges, patterns). Output schemas are defined but not visible in source excerpt. Error handling exists in client code but tool-level error guidance is absent. No tool annotations (readOnlyHint, destructiveHint). Missing parameter descriptions for 'model' and 'searchType' fields.

• Add explicit descriptions to 'model', 'searchType', and 'format' parameters. E.g., 'model: The search provider backend (e.g., google, bing). Defaults to configured provider.'
• Convert 'searchType' to an enum with documented options (web, news, images, etc.) instead of free-form string.
• Enhance tool descriptions with decision guidance: 'Use web_search to find recent information and links. Use web_fetch to extract full content from a specific URL. Call web_search first if you don't have a URL.'
• Add readOnlyHint: true to both tools in registerTool() to signal they are safe to retry and have no side effects.
• Document output schema fields in code comments or a separate schema file, ensuring all chaining IDs (e.g., provider, query) are present for downstream tool composition.

Inferred effective spec: 2025-06-18+.

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