Smart Search

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and partial results are known. The description adds valuable context beyond annotations: order number search uses 'Gorgias server-side full-text search across ticket subjects, messages, and metadata,' and it discloses auto-detection limitations for ambiguous numeric queries. It does not mention pagination or result format, but the annotation coverage lowers the burden.

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 three sentences, but every sentence adds critical value: the purpose, usage guidance, and a follow-up tool reference. It is front-loaded and free of filler or redundant restatement of the title.

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 tool's complexity (6 parameters, 2 enums, no output schema), the description addresses the main ambiguities an agent might face, such as when to use search_type and what the order number search covers. It lacks explicit details about return structure or pagination, but the schema's limit parameter and the mention of 'tickets, customers, and views' provide sufficient context for initial invocation.

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 100%, and each parameter already has a meaningful description. The tool description enhances the semantics of the query and search_type by explaining when to set search_type explicitly and how auto-detection handles different input types. It also clarifies the underlying search behavior for order numbers, going beyond the schema's enum descriptions.

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 an 'Intelligent search across tickets, customers, and views,' giving a specific verb and resource. It does not explicitly contrast with the sibling gorgias_search, but the phrase 'smart search' and the detailed discussion of auto-detection differentiate it enough. It could be clearer about how it differs from gorgias_search.

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?

Provides explicit guidance on when to use the search_type parameter: 'Use the search_type parameter when intent is clear from context' and especially for ambiguous numeric queries. It also explains the strengths of auto-detection for emails, keywords, view names, and customer names. It names gorgias_smart_get_ticket as the alternative for viewing full conversations, but does not discuss when to prefer other search-related siblings like gorgias_search.

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