atlas_codebase_surgeon

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

The description mentions 'Dry-run mode for safe testing' and 'Auto-rollback generation,' which are positive behavioral disclosures. However, it fails to convey the autonomous, potentially destructive nature of the tool, and claims like '100% accuracy' are misleading. With no annotations, the description should more clearly warn about the risk of large-scale mutations and the need for validation. This is a significant transparency gap.

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 overlong and full of marketing hype ('Revolutionary capabilities far beyond basic refactoring'). While the title is front-loaded, the bullet list contains repetitive claims and unsupported superlatives. A concise paragraph stating the core functionality and key parameters would be more effective.

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?

With no output schema and a nested operation object that lacks type-specific parameter definitions, the description should explain return values, error handling, and the full scope of each operation. It only vaguely references features like 'blast radius analysis' without explaining what the agent can expect. The lack of information about the tool's output and operation details makes it incomplete for a complex tool.

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 100%, so baseline is 3. The description adds value by explaining several operation types (e.g., 'semantic code transplant,' 'cross-file rename') through its capability list, giving more context to the operation enum. However, it does not detail the type-specific parameters for each operation, so it does not fully compensate for the vague nested operation 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 identifies the tool as a multi-file refactoring engine with a specific verb and resource ('AUTONOMOUS MULTI-FILE SURGICAL REFACTORING ENGINE'). It lists concrete operation types and scopes to multi-file changes, which distinguishes it from simpler refactoring tools. However, it does not explicitly contrast itself with the sibling atlas_refactor, so differentiation relies on the multi-file emphasis.

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?

It explicitly states 'Use this for surgical precision code modifications that affect multiple files,' which tells the agent when to select this tool. It does not mention alternatives or exclusion criteria, but the context is clear enough for basic selection. The lack of a 'when not to use' statement prevents a 5.

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