brand_resolve_conflicts

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

With no annotations, the description explains both modes (show lists conflicts, resolve commits a winner), return types, and a follow-up step. It could be more explicit about destructive nature, but overall adequately transparent.

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 front-loaded with purpose, then details modes, usage, exclusions, and post-conditions. Every sentence adds value, though slightly verbose in examples. Efficient overall.

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 no output schema and 3 params, the description covers return types, prerequisites, and follow-up action. It mentions config file source_priority. Could elaborate on default behavior of show mode without field, but adequate.

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 coverage is 67% with field and source having descriptions. The description adds context: mode enum values are clear, field examples like 'colors.primary', and source list. Meaningful addition beyond schema.

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 inspects and resolves disagreements between brand sources with specific examples (web, Figma, PDF). It distinguishes from siblings like brand_audit and brand_audit_content by specifying it is NOT for validating structure or scoring content.

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?

Explicitly states when to use: when brand_audit reports conflicts, after ingesting multiple sources, or when inconsistencies appear. Also provides exclusions (not for validation/scoring) and a post-condition (run brand_compile).

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