create_report

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

With no annotations, the description fully discloses key behaviors: no clobbering, default page_setup, atomic save with .tmp and rename, structural and XSD validation, and the return value. It could mention error handling for invalid input, but current detail is strong.

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 core action and provides important details in a logical order. While slightly long, it avoids unnecessary words and earns each sentence with specific information like defaults and validation.

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 no output schema, the description includes the return fields. It covers creation from scratch, default values, and validation. It could mention what happens if validation fails, but overall it provides sufficient context for the tool's role alongside siblings.

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 coverage is 0%, so description compensates well. It explains path as the output location, datasource as a forward-compat hook with wiring details, and page_setup as an override for defaults. This adds meaningful context beyond the schema's type-only definitions.

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 tool creates a new RDL report from scratch at a given path, with the phrase 'Emit a minimal valid RDL from scratch'. This distinguishes it from siblings that modify existing reports, as the sibling list includes many tools for adding elements to reports.

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 implies usage scenarios: use this to start a new report, as it refuses if the path exists (no clobbering). It also explains when to provide datasource and page_setup overrides. However, it does not explicitly state when not to use it or compare to alternatives like raw_xml_replace or duplicate_report.

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