Batch Diagnose Builds

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes further by revealing that the tool runs diagnose_build(brief=True) in parallel, returns a compact classification summary, and enforces a max of 20 UUIDs. This adds behavior context beyond the annotations, but it does not discuss error handling or partial failure behavior, which would be valuable.

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 tightly structured: it opens with the core purpose, then explains the execution model, then gives usage alternatives, and finishes with an Args list. Every sentence earns its place, and the content is front-loaded. No padding or redundant statements.

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 batch nature and the availability of an output schema, the description covers all essential context: what it does, how it works, when to use it, parameter constraints, and return style. The presence of an output schema means detailed return field documentation is unnecessary here. The description is complete for selecting and invoking this tool 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?

Schema description coverage is 0%, so the description must carry parameter semantics. It does so effectively: 'uuids: List of build UUIDs to diagnose (max 20)' and 'tenant: Tenant (default from env)' add constraints and defaults not present in the raw schema. This provides actionable meaning for both parameters, though it could be slightly richer (e.g., UUID format hints).

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: 'Classify multiple failed builds in one call — returns a triage table.' It clearly distinguishes from the sibling diagnose_build by stating 'Use instead of calling diagnose_build N times when triaging multiple failures.' This explicitly identifies the tool's unique role in the batch context.

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 provides explicit usage guidance: 'Use instead of calling diagnose_build N times when triaging multiple failures.' It also explains the mechanism (runs diagnose_build(brief=True) in parallel) and implies the single-build alternative is diagnose_build, giving clear context for selection.

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