Keyword (BM25) search

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

With no annotations provided, the description carries the burden of explaining behavior. It mentions tokenization, stemming, relevance scoring, and the inclusion of '_id' and 'score' in results. While it doesn't explicitly state the operation is read-only, the nature of a search tool implies it, and the description gives sufficient detail about what happens during execution.

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 flow: use case, mechanism, behavior, and alternatives. However, some redundancy exists (e.g., repeating 'matches exact tokens, not synonyms or paraphrases' twice and the phrase about literal terms). It could be tightened without losing meaning, but it remains concise and easy to scan.

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 fully contextualizes the tool within its sibling set, covering when to use it, how it differs from alternatives, and what to expect in terms of output (relevance scores, columns). It also touches on default behavior (e.g., column inference), making it complete for a search tool without needing to explain the return schema, which is already in the output 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 schema covers all 5 parameters with descriptive text (e.g., 'column' explains inference from table schema, 'columns' details return behavior). The description reinforces these but adds minimal new information beyond contextual usage (e.g., mentioning 'identifiers, error codes' as example queries). Given the high schema coverage (100%), the description adds modest value, warranting a score above baseline.

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 performs BM25 full-text search and ranks results by relevance, specifically for literal terms like identifiers and error codes. It also distinguishes itself from sibling tools (semantic and hybrid search) and SQL LIKE, making its purpose unambiguous.

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 advises using this tool for literal term queries and exact phrases, and directs users to alternative tools for meaning-based search (infino_semantic_search) or combined use (infino_hybrid_search). It also recommends preferring this over SQL LIKE for known literal terms, providing clear 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.