commerce_dashboard_summary

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

Does not disclose any behavioral traits beyond the annotations. Given that the annotation indicates `destructiveHint: true`, the description should clarify what destructive actions might occur, but it simply says 'Run' without discussing side effects, data modification, or required permissions. The phrase 'under your JWT, tenant, and company scope' adds context about authorization but not about behavior.

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 concise and well-structured, starting with the main action, then explaining routing, and finally listing arguments. It avoids unnecessary detail and stays focused. The only slight inefficiency is the routing phrase, which, while relevant, could be considered supplementary. Overall, it is appropriately sized and front-loaded.

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 contradictory annotations (`readOnlyHint: false` and `destructiveHint: true`), the description does not resolve the ambiguity about whether this tool modifies data or is safe. It also fails to mention what the `dashboard_summary` action returns or include any output schema details. The description is incomplete for an agent to fully understand the tool's behavior and expected results.

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?

Provides some meaning for both parameters: `message` is described as a 'free-text objective' and `inputs` as an 'optional JSON string of structured inputs.' While this gives a basic understanding, it lacks specifics on what kind of objectives or inputs are expected, and no examples are provided. The descriptions are too vague to fully compensate for the lack of schema-level documentation.

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?

States a clear verb ('Run') and a specific resource ('commerce domain agent action `dashboard_summary`'), making its primary function obvious. It does not explicitly compare itself to sibling tools like `dispatch_domain_agent`, but the specificity of the action name provides enough distinction. The additional context about routing through the dispatcher further clarifies its role.

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 no guidance on when to use this tool versus alternatives. It explains how it routes (via the domain-agent dispatcher) but does not mention conditions, prerequisites, or cases where another tool would be preferred. The description lacks any 'use when' or 'instead of' directives.

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