Build Failure Analysis

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

The annotations already declare readOnlyIntent and idempotent behavior, and the description goes beyond this by revealing that it parses job-output.json and returns precise failure data (task, host, error). It also distinguishes its behavior from diagnose_build, providing useful context about what it does not do (classification/log context).

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 concise and well-structured. It opens with a clear purpose statement, follows with the parsing behavior and sibling alternative, then lists parameters. Every sentence adds value with no redundancy or fluff.

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?

With an output schema present, the description does not need to explain return values. It covers the core purpose, the specific data source (job-output.json), and parameter semantics. The only minor gap is the lack of explicit mention of behavior when no failures are found, but given the output schema and annotations, this is adequate.

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 input schema has no parameter descriptions (0% coverage), but the description includes an Args section that explains each parameter: uuid, tenant (with default from env), and url (as an alternative to uuid+tenant). This compensates well for the schema's lack of detail, though it could be more elaborate with format or precedence rules.

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 analyzes a failed build and identifies which task failed, on which host, with the error message. It also distinguishes itself from the sibling tool diagnose_build by noting it provides raw failure data, making its unique role clear.

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 explicitly recommends diagnose_build for most use cases, citing that it adds classification and log context, which gives the agent a clear alternative. However, it does not specify the exact scenarios where get_build_failures should be chosen instead, so the guidance is slightly incomplete.

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