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

The description goes well beyond the annotations (readOnly, idempotent, non-destructive) by detailing what a done job includes (authored markdown, optional saved art_direction_id), what iteration jobs expose (source ID, expected revision, apply outcome), and what a failed job provides (per-source status, safe failure reason). This gives the agent a clear behavioral model for expected outputs and failure modes.

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, opening with the core purpose in one sentence. Each subsequent sentence adds distinct value (polling semantics, done job payload, iteration specifics, failure handling). No superfluous words or repetition.

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 absence of an output schema, the description sufficiently explains return values and states: done vs failed, what each contains, and special cases for iteration jobs. It also covers the async polling pattern and save flag behavior, making the tool's behavior fully understandable for a complex async operation.

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?

The schema already describes job_id with 100% coverage, but the description adds important context by clarifying that the job ID can come from either author_art_direction or iterate_art_direction, extending the schema's mention of only the former. This enriches the agent's understanding of valid inputs.

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 purpose: to read an asynchronous ArtDirection authoring job. It uses a specific verb ('Read') and resource ('ArtDirection authoring job'), and distinguishes itself from sibling tools like get_art_direction by focusing on polling job status rather than fetching a direct entity.

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 provides clear usage context: poll the job ID returned by author_art_direction or iterate_art_direction until done/failed. It names the source functions and describes polling behavior. However, it does not explicitly state when not to use this tool or mention alternatives like get_art_direction for direct retrieval, so it stops short of a 5.

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