route_query

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

Describes the tool as deterministic based on graph depth, and lists return fields (model_tier, reasoning_approach, why, context subgraph). No annotations are provided, so the description carries the full burden. It is fairly transparent, though it does not mention error handling or auth requirements.

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: purpose, mechanism, routing table, args, returns. It is detailed but not excessively long. Some sentences are slightly verbose but add 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?

For a single-parameter tool with an output schema, the description sufficiently covers input type and return fields. It lacks details on error scenarios or performance, but overall is complete enough for an AI agent to use.

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 description explains that the 'question' parameter can be a 'Concept name or natural language question about Salesforce AgentForce,' adding meaningful context beyond the schema's title 'Question.' With schema description coverage at 0%, this compensates well.

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 ('Route') and the target ('AgentForce question to optimal model and reasoning approach'). It distinguishes itself from sibling tools like list_concepts, search_concepts, and query_ckg by focusing on routing to models rather than querying or listing concepts.

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 routing logic with a table mapping hop depths to models and reasoning approaches. It explains that the CKG graph decides deterministically. However, it does not explicitly state when to avoid this tool or compare it with alternatives like query_ckg.

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