ask_about_diff

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

Annotations already indicate safe, read-only behavior. Description adds that it combines git diff, vector search, and LLM synthesis, and mentions no indexing required. Adds useful context beyond annotations without contradiction.

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?

Concise and front-loaded: three sentences plus a note. Every sentence adds value, no redundancy or filler.

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?

Describes the tool's mechanism and alias but lacks information about the return format (e.g., plain text, structured). With no output schema, the description should hint at the nature of the response. Otherwise, it adequately covers the 5 parameters and usage context.

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?

Input schema has 100% coverage with descriptions, so baseline is 3. Description adds context about the process (RAG, diff) but doesn't significantly enhance parameter meaning beyond what schema already provides.

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?

Clearly states the tool answers questions about recent code changes using RAG, with concrete examples like 'What changed?' or 'Are there any bugs?'. Explicitly notes it's an alias for analyze_diff with mode='question', distinguishing it from sibling tools.

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 context for when to use (questions about recent code changes) and states 'No prior indexing required'. Identifies as alias for a specific mode of analyze_diff, implying alternatives. Lacks explicit when-not-to-use or exclusion criteria.

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