pplx_smart_query

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

With no annotations, the description fully discloses behavior: quota-awareness, automatic model selection, intent-based routing to specific models (e.g., 'quick routes to Sonar 2'), and that responses include a metadata block with model, routing reason, and quota snapshot. Also mentions scarce monthly quota for research and that user must explicitly request it.

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?

Well-structured with bullet points for intent guide, front-loaded with purpose and usage recommendation. Some redundancy (e.g., repeating 'default to quick' and 'intent guide') but overall efficient. Could be slightly more concise without losing clarity.

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 tool complexity (quota-awareness, multiple models, intents, source_focus) and presence of an output schema, the description covers most aspects needed to use the tool correctly. It references related tools (pplx_usage, pplx_connectors). However, it omits explanation of conversation_id and does not address error handling or quota exhaustion scenarios.

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?

Despite 0% schema description coverage, the descriptions for query, intent, and source_focus add significant meaning (e.g., explaining intent levels, source_focus options including connector source ID). However, conversation_id is not explained, and there is a slight inconsistency where schema default for intent is 'standard' but the description recommends defaulting to 'quick' for most lookups. Coverage is incomplete.

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's purpose: 'quota-aware query' that checks limits and picks the best model automatically. It is explicitly labeled as 'RECOMMENDED DEFAULT TOOL,' distinguishing it from siblings like pplx_sonar and pplx_deep_research by its automatic model selection and quota management.

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?

Very explicit about when to use: 'USE THIS FOR EVERY QUERY unless the user explicitly requests a specific model.' Provides detailed intent guide with specific criteria for each level (quick, standard, detailed, research), including when to escalate. Clearly differentiates from sibling tools by recommending this as the default.

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