commerce_product_analysis

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the description is not the sole source of safety information. The description adds useful context that execution occurs under JWT, tenant, and company scope, and that it routes through a dispatcher. However, it does not disclose what side effects may occur, what data may be mutated, or how the action's behavior may vary, leaving the destructive nature abstract.

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 compact and well-structured: an opening purpose sentence, a routing/scope sentence, and a clean Args list. Every sentence contributes information, and the parameter descriptions are front-loaded and easy to parse. There is no unnecessary filler.

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?

Despite having an output schema, the description is incomplete for a generic domain-agent dispatcher tool. It provides no examples of valid messages, no guidance on what 'inputs' should contain, and no differentiation from the sibling 'product_analysis' tool. Given the huge sibling list and the generic nature of the action, an agent would likely struggle to construct a correct 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 description coverage is 0%, so the description must compensate for the bare input schema. It provides brief semantic labels: 'message' is a 'free-text objective' and 'inputs' is an 'optional JSON string of structured inputs'. This is minimally helpful but still vague; it does not explain how to format the message, what keys are expected in 'inputs', or what constitutes a valid structured input for product_analysis.

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 verb ('Run') and the resource ('the commerce domain agent action product_analysis'), so an agent can identify what operation is being invoked. It also explains it routes through the platform's domain-agent dispatcher, distinguishing it as a wrapper. However, it does not explain what 'product_analysis' actually analyzes, and the existence of a sibling tool named 'product_analysis' creates potential ambiguity that is not resolved.

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 gives no guidance on when to use this tool versus alternative commerce/product tools such as 'product_analysis', 'commerce_product_graph_query', or 'commerce_chat'. It only states routing context (JWT, tenant, company scope) but no selection criteria, exclusions, or preferred use cases. This leaves the agent to infer when this dispatcher-based action is appropriate.

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