search_documents_semantic

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

No annotations are present, and the description only mentions 'when available' without disclosing what happens if FAISS embeddings are not available (e.g., error, fallback, empty results). It also does not mention any auth, side effects, or output format.

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 concise and to the point, with no unnecessary words or fluff. It fits in a single sentence and effectively communicates the core functionality.

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 tool lacks crucial context such as return format, error handling, and how it differs from sibling search tools. Given the existence of multiple search tools in the sibling list, a brief note on when to prefer semantic search would significantly improve completeness.

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 schema defines 'query' as a required string and 'limit' as an integer with a default of 5, but the description provides no additional meaning. Parameters like 'query' are obvious, but 'limit' could have implications (e.g., max results) that are not explained.

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 action ('Search'), the specific resource ('local research documents'), and the method ('FAISS embeddings'), which distinguishes it from a plain full-text search sibling like 'search_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?

The description does not provide any guidance on when to use this semantic search versus the sibling 'search_documents' or 'search_documents_vector'. The phrase 'when available' hints at a conditional behavior but does not explain fallback or selection criteria.

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