suggest_fix

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering safety. The description adds that output includes patch, confidence, framework_confidence, and needs_human_review, plus framework detection via nearest package.json, providing behavioral detail beyond annotations.

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 sentences (though second is fragmented) are reasonably concise. Purpose is front-loaded. Some redundancy (e.g., listing frameworks) but overall efficient.

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 an output schema exists, the description covers all necessary aspects: input parameters, modes, output summary, framework detection, and integration with sibling tools. No gaps for the complexity level.

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 baseline is 3. The description adds value by explaining single vs batch mode (finding_id vs finding_ids) and mentioning optional file_content/file_path for better accuracy, augmenting the schema's concise descriptions.

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 a 'PRIMARY framework-aware fix generator' that produces search/replace patches for various frameworks. It explicitly distinguishes from sibling 'generate_patch' as the legacy variant, leaving no ambiguity.

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?

Provides clear usage instructions: pass finding_id + audit_id, single or batch mode, and suggests piping to generate_pr or run_verification_suite. Does not explicitly mention when not to use, but context is sufficient.

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