create_report

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

Beyond the destructiveHint annotation, the description discloses non-obvious behaviors: the atomic creation with operations, the risk of leaving an empty report behind if later edits fail, VA prepending an empty default Page 1, and the result's verify_hint. These details meaningfully exceed what the annotations alone communicate.

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 front-loaded with the main purpose and each sentence earns its place by adding actionable detail: return payload, atomicity rationale, follow-up editing, and export verification caveat. It is dense but not bloated.

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 mutating report-creation tool with four parameters, the description covers the full workflow: create, identify what was created, edit later, and verify output. It also includes a non-obvious export caveat, while structured annotations and output schema cover the remaining context.

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 already covers all four parameters at 100% coverage, which provides the baseline. The description adds value by explaining that operations uses the same shape as apply_report_operations, is applied atomically at creation, and that describe_report_objects should be consulted for formats.

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 opens with a specific verb and resource ('Create a Visual Analytics report') and states that the returned id is for further edits. It also distinguishes the empty-shell creation mode from the atomic full-build mode, which separates this tool from siblings like apply_report_operations and copy_report.

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 workflow guidance: pass operations to build the whole report atomically at creation, then feed the returned id to apply_report_operations for further edits. It also tells the agent to verify page-by-page with export_report due to the prepended default Page 1. It does not explicitly enumerate alternatives like copy_report, but the context is strong.

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