Run Code Analyzer (PMD/ESLint/RetireJS/SFGE)

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

While annotations already declare read-only and idempotent, the description adds substantial behavioral detail: it retrieves class bodies via Tooling API, creates a temp workspace, cleans up afterward, requires Java 11 for certain engines, and automatically falls back to Java-free engines with a response flag. This goes far beyond the annotation hints.

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 information-dense and front-loaded with the core purpose, but the first sentence is quite long with a parenthetical list of engines and rules. The param descriptions are concise and add value, but the overall length is higher than strictly necessary though each sentence carries meaningful detail.

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 covers the multi-engine nature, Java dependency, fallback behavior, and lifecycle (fetch, scan, cleanup). It does not detail the exact output format or return schema, but it does mention response flags for fallback. Given no output schema, a bit more about the scan results could improve completeness, but it is largely adequate 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%, and both the schema and description explain classNames, maxClasses, and ruleSelector defaults. The description adds little beyond the schema, mainly reiterating defaults and the Java fallback context. Baseline 3 is appropriate given the schema does the heavy lifting.

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 running Salesforce Code Analyzer against Apex classes, listing specific engines and rules. It distinguishes itself from the sibling sf_scan_apex_antipatterns by framing itself as a real multi-engine scan on top of the lighter heuristic check.

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 positions the tool relative to sf_scan_apex_antipatterns, implying deeper analysis. It explains the Java-dependent engine fallback behavior, giving clear context for when certain features are unavailable. However, it does not explicitly state 'use this when X, use antipatterns when Y'.

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