repo_ask_codebase

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It does mention the use of a generative LLM (Qwen2.5-Coder), which implicitly signals probabilistic, non-deterministic output. However, it does not disclose potential latency, token limits, failure modes, or the need for prior indexing, which are relevant for a retrieval-based tool.

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 tight sentences: the first states the core purpose, the second explains the technical approach. No wasted words, information density is high, and the most important detail (asking a question) comes first.

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?

For a relatively simple tool with 3 params, no output schema, and no annotations, the description covers the essence: what it does and how it works. It could mention the response format or that the answer is generated by an LLM (it does imply that), but the lack of such detail is a minor gap. The prerequisite of an indexed codebase is stated, which is key.

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?

The input schema provides descriptions for 100% of the parameters, including default and range for maxChunks. The description adds no extra parameter-level detail beyond what the schema already provides, such as the meaning of 'natural language' or how repo_path is matched. Baseline of 3 is appropriate because the schema covers the heavy lifting and the description does not conflict.

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 verb 'Ask' and the resource 'indexed codebase', making its purpose obvious. It also specifies the underlying technology (RAG over ChromaDB, Qwen2.5-Coder), which adds precision. However, it does not explicitly distinguish this tool from sibling repo_* tools like repo_query_knowledge_graph, though the natural language emphasis provides implicit differentiation.

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 phrase 'about an indexed codebase' implies a prerequisite that the codebase must have been indexed, but it does not explicitly say to use repo_index_repository first or explain when to use this tool versus alternatives. The context is clear but no exclusions or alternative guidance is given.

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