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

The annotations are all false/neutral, so they carry little safety information. The description compensates by disclosing that builds create durable owned objects, that JSON/deck tiers are re-runnable, and that 'failed builds are never billed' — useful behavioral and financial context beyond the structured fields.

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 purpose is front-loaded in the first sentence, and the four tier definitions are compact and scannable. Every sentence carries distinct information about required input, timing, or ownership, with no 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?

For a 7-parameter tool with nested objects and no output schema, the description covers the critical decisions: which tier to pick and the easiest parameter combination. It does not describe the response/return value or the legacy specification path, but the schema covers parameters and sibling tools like build_status can cover post-submission tracking.

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?

With 100% schema description coverage, the baseline is 3; the description adds real value by detailing each tier's meaning, declaring tier as required even though the schema lists no required fields, and recommending the simplest parameter combination. It does not explain the legacy specification object, but the schema already documents it.

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: 'Commission a NEW analysis built for your question.' The word NEW distinguishes it from siblings like modify_analysis and run_analysis, and the tier breakdown clarifies the exact product being created.

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?

It clearly frames when to use the tool (commissioning a new analysis) and tells the agent the easiest invocation ('fuzzy_request + dataset_ref + tier'). It also explains how to pick a tier by describing each option, but it does not explicitly name alternatives or state when not to use the tool.

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