get_workflow_aggregates

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

No annotations are provided, so the description bears the full burden. It discloses key behavioral traits: the query fails without a group_by_* flag, select_* flags control which aggregate values populate, and it documents the return shape in detail. It does not explicitly state whether the operation is read-only or mention permissions/auth, but the tool name and description imply a safe read operation. It adds meaningful context about failure modes and output structure beyond what annotations would offer.

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 appropriately sized for a 23-parameter tool. It leads with a clear purpose and concrete use case examples, then systematically presents Args and Returns. Every sentence earns its place: the examples illustrate semantics, the Args list is complete, and the return structure is explicit. There is no redundant fluff or vague 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?

Given the tool's complexity and the absence of parameter descriptions in the schema, the description is entirely sufficient. It covers all 23 parameters, explains the required selection of group_by_* and select_* flags, describes the failure scenario, and details the return object structure. The output schema exists, but the description goes beyond it by explaining the meaning and relationships between parameters, making it easy for an agent to invoke correctly.

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 schema provides only titles and defaults, with 0% description coverage. The description fully compensates with a detailed Args list explaining each parameter's meaning, type, default, and required status. It clarifies the purpose of select_* and group_by_* flags, and describes filter parameters like status, time windows, and workflow_id_prefix in actionable terms. This is a model of how to document intricate parameters.

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 a specific verb and resource: 'Get workflow aggregate metrics from DBOS Conductor.' It distinguishes this tool from siblings like list_workflows by emphasizing aggregated, grouped metrics for dashboards and status-at-a-glance, with example questions that illustrate its unique purpose.

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 clear context: it's for dashboards and understanding workflow status, with concrete examples like counting failed workflows or pending per queue. It also states mandatory requirements: at least one select_* flag and one group_by_* flag, and explicitly warns that a query with no group_by_* will fail. However, it does not explicitly compare to alternatives such as list_workflows or get_workflow, so it lacks direct 'when not to use' guidance.

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