smart_search

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

With no annotations provided, the description carries the full burden and meets it thoroughly. It discloses read-only status ('Read-only. No side effects.'), performance characteristics ('Slow (10-30 s)'), the full multi-phase pipeline (translate → rough_search → ... → format), and fallback behavior ('When LLM is unavailable, falls back to direct FTS5 search'). This gives the agent complete expectations about side effects, latency, and internal behavior.

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 well-structured with a clear intro, a multi-phase breakdown, and a fallback note. It is longer than most, but each phase is informative and explains the internal behavior. There is some redundancy: the 'Prefer this when...' guidance appears twice (once in the intro, once in the 'When to prefer' section), which could be trimmed. Overall, it is organized and front-loaded with the most critical usage guidance.

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 is fully self-contained for a complex tool. It covers purpose, usage criteria, performance, internal pipeline, fallback semantics, parameter guidance, and return format (metadata keys and symbol result fields). The output schema exists, but the description further explains what the returned list contains, making it complete even without inspecting the schema.

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 input schema already covers all three parameters with 100% coverage, so the baseline is 3. The description adds value beyond the schema by advising 'Be specific — 5–15 words works best' for the query, clarifying that project_root is 'Auto-detected from CWD if omitted,' and noting the limit default and maximum. These are practical usage nuances that help the agent craft better parameters.

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 starts with 'Natural-language search: an LLM generates FTS5 keywords, then searches the libclang index' — a specific verb+resource statement. It clearly distinguishes itself from exact-text tools like search_code by noting it 'finds concepts by meaning rather than exact text match.' This makes the tool's purpose unmistakable.

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 explicitly states 'Prefer this when you don't know the exact keywords and want to describe what you're looking for,' with concrete examples. It also has a dedicated 'When to prefer over search_code' section, naming the alternative and the exact condition for choosing this tool. This is exemplary when-to-use guidance.

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