Diagnose Build Failure

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive. Description adds behavioral details: structured failures plus log context, and additional fields for analysis, enhancing transparency beyond annotations.

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?

Description is front-loaded with purpose and value proposition. Could be slightly more terse but is well-structured with no wasted sentences. Minor redundancy in the arg list at the end.

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 what the tool does, benefits, and what it returns. Mentions output fields (ref_url, project, change, files_in_failure). With output schema present and good annotations, the description is complete for an agent to understand usage.

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 coverage is 0% but description provides minimal parameter guidance: lists uuid, tenant, url with brief notes ('uses default if empty', 'alternative to uuid+tenant'). Adds some meaning beyond schema but still leaves some ambiguity. Baseline 3 for low coverage with some compensation.

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 diagnoses build failures by combining failure info and log context. It distinguishes from siblings by explicitly naming get_build_failures and get_build_log as separate calls to avoid.

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 advises to use this tool instead of calling get_build_failures and get_build_log separately, providing clear when-to-use guidance. Also explains the added value of returning ref_url, project, change, files_in_failure for pre-existing checks.

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