Flaky Job Detection

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

Adds beyond annotations: describes fetching builds, computing statistics, and the 'flaky' threshold (>20% failure). Annotations already declare safe, read-only, idempotent nature.

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?

Concise two-paragraph structure: purpose/logic first, then parameter list. Clear and well-organized, with no extraneous text.

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 5 parameters, comprehensive annotations, and output schema, the description covers purpose, behavior, and parameters completely. No gaps remain for agent to invoke 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 coverage is 0%, but the description provides full explanations for all 5 parameters (job_name, tenant, project, pipeline, limit) with defaults and meanings. Fully compensates.

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?

Clear verb 'detect' with specific resource 'flaky jobs'. Distinguishes from sibling tools like list_jobs (lists all) and get_build_failures (gets specific failures).

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?

States when to use: to identify flaky jobs from build history. Doesn't explicitly exclude cases but context of siblings implies use case. Could mention alternatives for single-failure analysis.

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