index_repo

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

With no annotations, the description bears full burden. It discloses the token range (~500-700) and explains merge behavior for exclude_dirs. Missing details on whether indexing is persistent, destructive, or requires permissions. Partial transparency.

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?

Description is concise, front-loaded with purpose and quick overview. Parameters are explained in a bullet-style format. No redundant sentences; efficient use of space.

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 return value and basic behavior but omits idempotency, cost (time/resources), and permission requirements. Given complexity (indexing tool) and lack of annotations, some gaps remain, but the token estimate and output format details help.

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 0%, requiring description to compensate. Description adds meaning for 'exclude_dirs' (merge with config) and 'output_format' (text vs json response). 'repo_path' is left to schema (default /demo) with no additional context. Incomplete but helpful.

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 'Build the semantic index and return a full orientation.' It specifies what it does and gives a list of outputs (project type, stats, top files, etc.). It distinguishes itself as the initial session setup tool, but does not explicitly compare to siblings like 'embed_repo' or 'file_map'.

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 says 'Run this once at session start,' providing a clear when-to-use instruction. However, it does not mention when not to use it or suggest alternative tools (e.g., 'search_semantic' after indexing), limiting guidance on tool selection.

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