evaluate_job

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

No annotations provided, so the description carries the full burden. It describes the operation as a write action recorded in the audit log, and notes asynchronous execution. Does not mention rate limits or other side effects, but covers key 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?

Description is concise with two main sentences plus an Args block. No superfluous text, every sentence adds value. Front-loaded with the core action.

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 triggers an async evaluation and does not return results directly; the description correctly points to get_job_evaluations for results. Given absence of output schema, this is sufficient. The description covers inputs, behavior, and post-operation steps.

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%, so description must compensate. It adds meaning to job_id by noting it must be a UUID of a job in 'success' or 'failed' state, and to rubric_id by referencing list_eval_rubrics. This goes beyond the bare schema.

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 specific verb-resource pairing: 'Trigger an LLM-as-judge evaluation of a completed job against a rubric.' It clearly distinguishes from siblings like get_job_evaluations and list_eval_rubrics.

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 explains that the evaluation runs asynchronously with results retrievable via get_job_evaluations, and specifies required job states ('success' or 'failed'). While it doesn't explicitly state when not to use, the context is clear.

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