Firefox BiDi MCP has 11 tools with basic naming and descriptions, but critical gaps in schema completeness and parameter documentation. Tool names follow verb_noun convention (firefox_bidi_*), which is good. However, most tools lack detailed parameter descriptions, many parameters have only 1-2 word descriptions ('Optional context ID'). Input schemas are present but minimal: most parameters lack type constraints, enums, or validation guidance. No output schemas are documented. Error handling is absent, tools do not guide recovery or categorize failures. The server is STDIO-only, which caps protocol readiness at 50 and limits real-world deployment.

• Expand parameter descriptions to 50-150 characters. For 'context' parameter, write: 'The BiDi context ID (tab/window). If omitted, uses the active context set by set_active_context(). Obtain context IDs from list_tabs().'
• Document output schemas for all tools. E.g., list_tabs should return: [{context_id: string, url: string, title: string}]. get_page_source should return: {html: string, encoding: string}.
• Add error handling guidance to tool descriptions. E.g., click_element: 'Returns error if selector matches no elements or multiple elements. Use get_element_text() first to verify selector matches exactly one element.'
• Add validation constraints to selector parameters. E.g., 'CSS selector (e.g., #button-id, .class-name, div > p). Must match exactly one element; returns error if 0 or >1 matches.'
• Create higher-level composite tools (fill_form, submit_form, wait_for_element) that wrap common multi-step sequences. This reduces agent reasoning overhead and improves reliability.