Build Failure Analysis

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

Discloses that it parses Zuul's structured job-output.json, and details response fields including ref_url, project, change, and files_in_failure. Annotations already confirm readOnly, idempotent, and non-destructive, and the description adds value without contradiction.

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 relatively concise and well-structured, with a clear front-loaded purpose and a separate Args block. Slightly longer due to usage guidance, but each sentence adds value.

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?

Covers purpose, usage, parameters, and behavioral context adequately. Given the presence of an output schema, the lack of output format details is acceptable. Could mention error handling or prerequisites, but overall sufficient.

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 has 0% description coverage, but the description includes an Args section explaining each parameter (uuid, tenant, url), including defaults and alternatives. This fully compensates for the missing schema descriptions.

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 it analyzes a failed build and returns exactly which task failed, on which host, with error message and return code. It distinguishes itself from sibling diagnose_build by noting that diagnose_build includes additional data, making the purpose distinct.

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?

Explicitly recommends preferring diagnose_build for most use cases due to its richer output, and provides guidance on using the returned 'files_in_failure' to determine if a failure is change-related or pre-existing.

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