Run Logs

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

Annotations already indicate read-only and non-destructive behavior, and the description adds valuable operational constraints: tail_bytes is capped at 25000 and absolute paths in log content are redacted. These details go beyond the annotations and help set agent expectations about limits and data privacy.

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?

Two focused sentences with no filler. The core action is stated first, followed by actionable usage guidance and key constraints. Every sentence earns its place.

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 tool is a simple read operation with an output schema available, so the description does not need to explain return values. The annotations cover safety, and the description provides usage timing, parameter limits, and redaction behavior, making it complete for an agent to select and 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 description coverage is 0%, but the description compensates by explaining the meaning of tail_bytes through 'bounded tails' and the explicit cap of 25000. It also clarifies that job_id refers to the job whose private logs are being read. It does not detail formatting or defaults, but the core parameter semantics are communicated.

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 uses a specific verb ('Read') with a clear resource ('bounded tails of a job's private log files'), making the tool's function immediately obvious. It is distinct from sibling tools like get_run_status or get_run_result, which deal with status and results rather than raw log content.

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 states when to use the tool: 'Use after a FAILED/TIMED_OUT/ORPHANED job to diagnose the cause before changing the strategy.' This is strong contextual guidance, though it does not name alternative tools or provide explicit when-not-to-use conditions.

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