pbi_repair_loop

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

Without annotations, the description adequately discloses the loop behavior: scanning, applying repairs when apply=True, saving, and rescaling until convergence. It also notes the requirement for a live connection for check_empty_visuals. However, it could be clearer about prerequisites (e.g., extract_folder must be an extracted report) and the permanence of modifications made by auto-repair.

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?

The description is concise and front-loaded with the loop concept, using technical terms efficiently. It could benefit from slightly better structure (e.g., separating phases) but remains free of redundant wording.

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?

Given the tool's complexity (6 params, iterative process, output schema exists), the description covers the main loop, repair types, and response contents (repairable_errors with llm_action). It could be more explicit about extract_folder and include_hidden, but overall it provides sufficient context.

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?

Despite 0% schema description coverage, the description adds meaning for several parameters: apply (default true), max_rounds (default 3), and check_empty_visuals (requires live connection). For extract_folder, implicit but not explicit; page and include_hidden are not described. This partially compensates for the schema gaps.

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's purpose as a 'Detect → classify → auto-repair → re-verify loop for a report extract,' using specific verbs and resources. It distinguishes itself from sibling tools like pbi_repair_report_fields by emphasizing the iterative loop nature.

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 context on when to use the tool (for automated iterative repair until convergence) and mentions the optional check for empty visuals with a live connection. However, it does not explicitly state when not to use it or mention alternative tools, leaving some ambiguity.

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