check_reachability

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

With no annotations, the description must carry the behavioral burden. It discloses the returned data (reachability status, path, etc.) and implies a read-only analysis by using 'trace', but does not state whether it modifies anything, requires special permissions, or has side effects. This is partial transparency but not comprehensive.

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?

A single, dense sentence that front-loads the action and lists the key outputs without redundancy. Every word earns its place.

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?

The description explains the tool's purpose and return values, but does not clarify the optional parameters (candidate vs. candidateJson, projectRoot), handling of absent candidate, or potential prerequisites. Given no output schema, an agent might not know how to construct the optional candidate object or when to rely on filePath alone.

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?

The input schema has 100% description coverage for all parameters, so the schema already provides meaning. The tool description adds no further parameter semantics, such as explaining the relationship between candidate and candidateJson or when to use projectRoot. Baseline 3 applies.

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 states a specific action ('trace data flow'), a specific resource ('scan candidate'), and enumerates the output components (reachability status, data-flow path, auth gates, sanitizers, confidence). It clearly differentiates from siblings like scan_file or analyze_code by focusing on reachability analysis for a candidate.

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 by specifying it applies to a scan candidate, but does not explicitly mention when to avoid it or name alternative tools. It provides context without exclusions, matching the 'clear context, no exclusions' level.

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