Three tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. toolchain_list and toolchain_show have minimal descriptions (under 100 chars). toolchain_exec lacks parameter descriptions for 'argv' and 'capture'. No output schemas documented for any tool. Parameter types are present but descriptions are sparse or missing. No error handling guidance, no recovery paths, no actionable error messages defined. Naming is reasonable (verb_noun pattern) but descriptions do not explain WHEN to use each tool or what distinguishes them.

• Document output schemas for all three tools. Specify the structure of returned data (e.g., toolchain_list returns {toolchains: [{name, version, ...}], registry: {...}}). Include field types and whether results are paginated.
• Expand tool descriptions to 100 - 200 characters. Explain WHEN to use each tool: 'toolchain_list: Discover available toolchains and their versions. Call this first to see what toolchains are registered.' Add prerequisites and dependencies.
• Add descriptions to all parameters. For toolchain_exec, document 'argv' as 'Command and arguments as a list (e.g., ["build", "--release"])' and 'capture' as 'If true, return stdout/stderr; if false, stream to console.'
• Add error handling guidance. Document common failures (e.g., 'hive not found', 'toolchain not registered', 'command failed with exit code X') and recovery steps. Include actionable error messages in responses.
• For toolchain_exec, add a confirmation step or dry-run mode. Destructive operations should require explicit approval or offer a preview before execution. Document the risk in the tool description.