Log Tail

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

Annotations already mark it as read-only, idempotent, and non-destructive. The description adds specific behavioral details: it's the fastest way to see failure reasons, and skip_postrun only applies to job-output.txt with a clear explanation. This enriches the agent's understanding beyond the 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?

The description is concise and well-structured. The first sentence captures the main purpose, followed by a comparative recommendation, and then a bullet-point style list of parameters. No unnecessary words, and the most important information is front-loaded.

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 the tool has 6 parameters, an output schema, and sibling tools, the description is fairly complete. It explains its role in the debugging workflow, parameter meanings, and a special behavior. However, it does not mention what the output looks like (though output schema may provide this) or any prerequisites. Still, it covers the essential context for effective tool selection.

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 description coverage is 0%, so the description carries the full burden for parameter clarity. It provides a brief but clear explanation for all six parameters, including defaults, max for lines, and the alternative use of url vs uuid+tenant. The skip_postrun parameter is well-explained. Some parameters could benefit from more detail, but overall adequate.

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 action: 'Get the last N lines of a build log'. It immediately connects to the purpose of seeing why a build failed, which is a specific, actionable use case. It also distinguishes itself from the sibling tool get_build_log by emphasizing token efficiency for tail needs.

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 using this as the first step when investigating failures and compares it to get_build_log(mode='summary') for token efficiency. It provides clear context, but does not explicitly state when not to use it (e.g., when full log is needed).

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