ask_question

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

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds that the tool uses RAG, returns answers based on relevant code context, and explains the agentic_rag parameter's effect (relevance grading and query rewriting). This adds valuable context 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?

The description is brief (three sentences plus example), front-loaded with the core purpose, and includes necessary prerequisite and example. Every sentence adds value with no redundancy.

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 the tool's complexity (RAG, optional agentic mode) and lack of output schema, the description could be more complete about the return format or what the answer looks like. It vaguely says 'Returns an answer', which is sufficient but not fully informative.

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 covers 100% of parameters with descriptions. The description adds an example and explains the behavioral implication of the 'agentic_rag' parameter, which goes beyond the schema's basic description.

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 asks questions about an indexed repository using RAG and returns an answer based on code context. It uses a specific verb and resource, and while it doesn't explicitly differentiate from siblings like 'query_codebase', the RAG aspect and prerequisite distinguish it implicitly.

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 explicitly states the prerequisite 'index_repository must be called first', and provides an example. However, it lacks guidance on when not to use this tool or alternatives, which would improve the score.

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