Build Failure Analysis

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds important behavioral context: it parses job-output.json, returns specific failure details, and warns about empty msg fields for no_log tasks. This provides transparency beyond the annotations 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 front-loaded with a clear summary sentence, followed by structured details and usage notes. While slightly verbose, every sentence adds value. The parameter list is separated for clarity.

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?

The description covers return fields (failed_tasks, ref_url, project, change, files_in_failure) and caveats (no_log). With an output schema present, it doesn't need to list every field, but additional guidance on interpreting the output could be beneficial.

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 0% description coverage, but the description includes an 'Args' section explaining each parameter: uuid (Build UUID), tenant (Tenant name, default if empty), and url (alternative to uuid+tenant). This adds crucial meaning that the schema alone doesn't provide.

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's purpose: analyze a failed build and return exactly which task failed, on which host, with error message and return code. It also mentions parsing Zuul's structured job-output.json. This distinguishes it from siblings like diagnose_build, which is explicitly recommended for most use cases.

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 guidance: 'For most use cases, prefer diagnose_build which includes all this data plus failure classification, log context, and timing details.' It also advises using the returned files_in_failure to determine if a failure is change-related, and notes the limitation of no_log: true tasks, directing users to get_build_log as an alternative.

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