sweep_dead_code

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

Even with no annotations, the description discloses the critical behavioral trait: 'Text-reference fallback counts CLI-string refs as alive (miss-over-delete bias)'. This is an honest limitation that helps the agent calibrate expectations. Also clarifies it is detection-only, pointing removal elsewhere, and states an exclusion.

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 two sentences, front-loaded with the purpose, and every phrase earns its place: categories, bias, removal path, and scope exclusion. No wasted words.

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?

For a tool with no output schema and a moderate parameter set, the description provides sufficient context: what it detects, its detection bias, how to act on results, and what is out of scope. It could mention the return format or signal structure, but that is a minor gap given the clarity of the description and schema.

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 the schema already documents all three parameters. The description adds no parameter-specific detail beyond what the schema provides, but it does mention 'unused_guard signal' as an output concept, not a parameter explanation. Baseline 3 is appropriate because the description doesn't need to compensate.

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: 'Detect dead code' and enumerates specific categories (unused imports/functions, orphan files). This is a specific verb+resource combination that distinguishes it from sibling tools like dep_graph or references.

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 gives clear context for use: detection of dead code with a bias toward false negatives. It explicitly notes out-of-scope cases (dynamic/reflection wiring) and points to edit_transaction for removal. However, it does not explicitly name alternative detection tools or state when to prefer this over dep_graph or references.

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