subsystem_index

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

No annotations are present, so the description carries the full burden. It explains the tool's scope (only file_summary and file_head records) and what it does not do (exact string matching), which is helpful. However, it does not explicitly state read-only behavior, return format, or potential side effects, though 'search' implies non-mutating.

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 compact and information-dense, using an example question to illustrate the intended use and a clear comparison with search_code. Every sentence adds value and there is no redundant 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?

The description provides sufficient context for a simple search tool: its purpose, scope, and relationship to alternatives. It does not explain return values, but the output schema exists and the tool is simple enough that this omission is minor.

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%, so the description must explain query and limit. It partially clarifies that query relates to repository structure questions and file summaries, but it does not describe the 'limit' parameter at all or give concrete query syntax. This leaves the agent guessing about an important parameter.

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 searches a file-level summary index, explicitly targeting repository structure questions and file-location tasks. It also distinguishes itself from the sibling search_code by noting it is better for file-location pinning.

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?

It provides explicit when-to-use guidance: repository structure questions like 'which file is this feature implemented in?' and states that exact string matching should use search_code (ripgrep) instead. This fully directs the agent toward the appropriate tool.

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