auto_remediate_compliance

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

There are no annotations, so the description carries the full burden for safety and behavior disclosure. It goes far beyond the basic operation: it discloses the actual LLM gate mechanics, the distinction between new and restored entities, the behavior of 'similar' proposals and fail-closed cases, and the convergence stop conditions. I cannot give a 5 because I don't see explicit disclosure about whether this tool is destructive (e.g., does it permanently create assets?) or requires additional permissions beyond PRO tier, but the level of detail about the conditional paths and gate behavior is substantial.

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 dense but well-structured. It leads with the purpose, then breaks down the phases, then the side-effect details, then the convergence and trigger. Every sentence contributes critical domain behavior or constraints (PRO tier, LLM gate, restore semantics, convergence, and auto-trigger). No filler or repetition. It is appropriately lengthy for a complex tool, and the structure makes it easy to parse.

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 (3 phases, LLM gate, multiple response fields, skipped reasons) and its lack of output schema and annotations, the description is remarkably complete. It covers the operation loop, the branching on restore-candidate gates, distinguishing new vs restored, skipped reasons, operator options for interventions, and convergence. It even links to the `add_asset` behavior for consistency. This is fully enriched for an operational with no annotations.

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 coverage is 67% (two of three params described), and the description adds no parameter-specific details. But it does mention that the tool operates on a 'framework' and a 'model' (from the IDs), which gives implicit context for those parameters. Since the schema already covers the most important parameters, the description does not need to repeat them, so this is a baseline 3; there is no added coverage above the schema's own coverage.

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 precisely states what it does: 'Automatically close compliance gaps for a framework', immediately followed 'Requires PRO tier.' and a detailed three-phase loop that explains the specific actions (auto-map, exclude, suggest/apply). It clearly distinguishes this from sibling tools like auto_map_controls or check_control_gaps by the phased behavior and the 'restore-candidate LLM gate' nuance. This goes beyond a simple verb+resource and provides a rich, differentiated purpose.

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 explicitly notes when this tool is triggered ('runs automatically when a framework is selected'), manual re-triggering ('can be re-triggered manually if the model changes'), and the conditions under which it stops (converges automatically). It also implies potential user intervention or a manual alternative (the lifecycle gate nuance). It doesn't explicitly name a specific alternative tool, but it clearly implies the usage context and when to use this versus a manual mapping process, which is sufficient given the role.

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