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

With no annotations, the description carries the full behavioral burden and handles it well: it explains result-shape differences between multi-output and single-output blueprints, the 10-minute signed URL TTL and need to re-fetch, and the special srt_text field for caption-video awaiting_review runs. No contradiction with annotations exists.

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 front-loaded with the core purpose and then adds only high-value behavioral specifics. Although longer than a one-liner, every clause covers a distinct aspect an agent needs to invoke or interpret the result correctly.

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 a single parameter, no output schema, and no annotations, this description covers output variants, TTL behavior, special status-specific fields, and how to continue a run. An agent has enough to call the tool correctly and interpret responses.

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 input schema has 100% description coverage for the single id parameter, so the baseline applies. The description does not need to add parameter details; it already explains the broader run context.

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 and resource: 'Fetch the current state of a blueprint run', and enumerates exactly what is returned (status, current step, outputs). This clearly differentiates it from sibling write/control tools like run_blueprint and continue_blueprint_run.

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?

Provides clear usage context: use this to poll status, re-fetch when signed URLs expire, and resume caption-video runs with continue_blueprint_run. It names the continuation sibling explicitly, though it does not mention other potentially relevant siblings such as get_download_url or run_blueprint_and_wait.

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