get_job_output

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

The description adds behavioral details beyond the readOnlyHint annotation: it works on running or completed jobs, returns partial output, and supports tail-based control. It doesn't describe output format or rate limits, but the annotation already covers safety, and these details are useful for expected behavior.

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 compact and front-loaded: purpose first, usage context second, and param docs last. Every sentence earns its place, and the param docs are formatted clearly with names and explanations.

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?

For a simple read-only tool with two straightforward parameters, the description covers purpose, usage, and parameter semantics. It implies text output via 'lines' and 'tail', which is sufficient without an output schema. No critical gaps remain.

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?

With 0% schema description coverage, the description compensates fully by documenting both parameters: job_id identifies the job, and tail specifies line count with default 100 and special meaning for 0. This adds significant meaning beyond the raw schema types and defaults.

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?

'Get partial output from a running or completed job' clearly identifies the specific verb (get), resource (job output), and scope (partial output). It distinguishes itself from sibling tools like get_job_status and list_jobs by focusing on output content rather than status or job listing.

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?

'Useful for checking progress before a job finishes' provides clear context for when to use the tool. It does not explicitly mention alternatives or exclusions, but the context strongly implies it is for progress monitoring on active jobs, and sibling tool names make alternative options obvious.

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