audit_and_fix_frankability

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries behavioral disclosure. It details file modification behavior, verify-or-rollback safety, the sampling-driven LLM loop, retry logic, and the exact return fields (schema, opId, findings, applied/skipped, rolledBack, baseline, finalState, llmRounds). This is comprehensive and accurate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Although long, the description is well-structured with clear mode headers and numbered steps. Every sentence either defines behavior, gives constraints, or explains mode execution. The length is warranted given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex (multi-mode, LLM integration, rollback), but the description covers all aspects: prerequisites, step-by-step flow, edge cases (retry, fallback), and return schema. No gaps are evident, even with no annotations and minimal schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description compensates richly: symbols_dir is defined as absolute path to symbols/ directory, mode enumerates valid values, aggressive is tied to medium-confidence fixes, and max_iterations caps prescriptions. It adds meaning far beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs frank-audit and optionally applies fixes, with explicit modes for report, safe-fix, and full. It references the specific resource (symbols dir) and distinct operations, distinguishing it from sibling tools that only audit, prescribe, or apply edits individually.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use each mode, including the difference between 'report' (no modifications), 'safe-fix' (mechanical fixes with rollback), and 'full' (adds LLM loop). It also notes prerequisites like MCP sampling support and explains graceful fallback when unavailable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.