job_output

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

No annotations are provided, so the description carries the full behavioural burden. It mentions 'tail of the run log' which hints at the tail_chars default behavior, but does not disclose whether this is a safe read-only operation, whether partial output indicates job completion, or any other behavioral traits.

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?

A single, tight sentence that front-loads the action and scope. No wasted words.

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?

An output schema exists, so return values need not be explained. However, with no annotations and 0% schema coverage, an agent still lacks clear guidance on permissions, whether the operation is read-only, and parameter details. Adequate but with clear gaps.

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 should compensate. It implies tail behavior ('tail of the run log') which gives some meaning to the tail_chars parameter, but job_id is entirely undocumented and no format or range details for tail_chars are given. Marginal value added, but does not fully compensate for the coverage gap.

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?

States a specific verb ('Read') and resource ('log output from a background job'), and clarifies the scope with 'tail of the run log'. This is distinct from job_status and job_kill among siblings, though it doesn't explicitly name those alternatives.

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 phrase 'Read more log output' implies this is a follow-up for fetching incremental output, and 'background job' implies it applies only to asynchronous runs. However, no explicit when-to-use vs job_status or job_kill guidance is provided.

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