index_directory

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

Without annotations, the description has high burden. It discloses the core actions (scan, extract, embed, store) but omits behavioral details like whether indexing is incremental or full, if overwrites existing data, handling of unchanged files, required permissions, or side effects on system resources.

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 well-structured sentences for the main purpose, plus a terse Args list. Every sentence is informative without redundancy. Excellent front-loading of the tool's primary action.

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 complexity (file scanning, embedding generation) and presence of an output schema, the description is partially complete. It covers input parameters and common file types but omits recursion behavior, handling of unsupported files, return value, and potential performance impact. The output schema may fill some gaps, but the description could still be more thorough.

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 adds needed meaning by clarifying directory_path as absolute path and ignore as optional glob patterns with examples. However, it does not specify pattern syntax or that ignore works on basenames versus full paths, leaving some ambiguity.

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?

Clearly states the tool scans a local directory, extracts text from specific file types and raw bytes from media files, generates embeddings using Gemini 2, and stores them for searching. This precise verb+resource combination distinguishes it from siblings like list_indexed_directories and search_my_documents.

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?

No explicit guidance on when to use this tool versus alternatives like sync_indexed_directories or remove_directory_from_index. It does not mention prerequisites, when to re-index, or when indexing is not appropriate.

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