buildCodebaseIndex

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

With no annotations, the description must disclose behavioral traits. It mentions scanning specific file types and calling an external API, but does not state whether the previous index is overwritten, the time/network cost, or any side effects. This is insufficient for a tool that has destructive potential (rebuilding index).

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 concise sentences. First sentence states purpose and scope. Second sentence provides essential usage guidance. No redundant words.

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?

Covers when to invoke but lacks details on what happens after invocation (e.g., progress indication, result, error handling). No output schema, so description should explain expected outcome or side effects. It is adequate but not complete for a complex indexing tool.

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 the schema already documents the single parameter dirPath with default and description. The tool description adds no further parameter semantics beyond what is in the 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?

Description clearly states it scans local JS/TS/JSX/TSX files and builds/rebuilds a vector index using Gemini Embedding API. It distinguishes itself from sibling searchCodebase by noting it must be called before first use of searchCodebase or after major code changes.

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 specifies when to use: after major code changes or before first use of searchCodebase. Does not provide alternatives or when not to use, but the context is clear that this is the only index-building tool among siblings.

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