scanner_run_dfa

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is carried structurally. The description adds nothing behavioral beyond that: no mention that it writes output files, that it is computationally heavy/long-running, or that JVM/thread/timeout tuning affects behavior.

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?

Two short, front-loaded sentences with no filler, and the core capability leads. It is efficient, though so terse that the brevity becomes under-specification rather than crispness.

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 nested 13-field analysis tool with no output schema, no annotation detail on returns, and heavy runtime configuration, the description is far too thin. It leaves format selection, severity thresholds, and output destinations entirely unexplained.

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?

Reported schema description coverage is 0% and the tool wraps a single nested 'input' object containing 13 tunable fields (target, projectDir, sfgeJvmArgs, pathExpLimit, thread settings, severity thresholds). The one-sentence description mentions no parameter at all, leaving the agent with no semantic guidance from the description side.

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?

States a specific verb and resource ('Run Graph Engine for Apex data flow analysis') and names the class of defect it finds, which distinguishes it from generic siblings like scanner_run. It stops short of explicitly contrasting with scanner_run, so an agent must infer when DFA is needed over the base scanner.

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?

No when-to-use guidance, no prerequisites (e.g., requires a project directory, JVM availability), and no routing against the obvious alternative scanner_run. The agent is told what it does but not when to pick it.

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