find_dead_code

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It mentions 'cross-module analysis' which is a useful behavioral trait, but it does not state whether the tool is read-only, what output format is returned, or any side effects. The description is better than a tautology but lacks depth—e.g., no mention of severity levels or how results are presented.

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 extremely concise: two sentences that state purpose and a key capability. It is front-loaded with the primary action and avoids unnecessary filler. Every word contributes to understanding the tool's scope.

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 (static analysis with a path, category, and severity filter) and the absence of an output schema, the description should explain what the results look like or what constitutes 'unused'. It mentions cross-module analysis to reduce false positives, which is helpful, but it does not describe the output format, how severity is assigned, or any limitations. The description is adequate but leaves the agent guessing about the return value.

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%—all three parameters have descriptions in the schema. The tool description does not add any extra meaning beyond the schema, so it reaches the baseline of 3. However, it does not elaborate on how parameters interact (e.g., how min_severity filters results or how category combines with path), missing an opportunity to add value.

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: detecting unused imports, functions, variables, and arguments in Python code. It also mentions cross-module analysis to reduce false positives, which differentiates it from generic code analysis tools. The verb 'detect' plus the resource 'dead code' is specific and distinguishes it from siblings like analyze_complexity or security_scan.

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 no guidance on when to use this tool versus alternatives, no prerequisites, and no mention of scenarios where it is appropriate. It neither says 'use this when...' nor 'for X, use Y instead'. Given the many sibling tools, this lack of context leaves the agent without direction on tool selection.

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