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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description adds genuinely useful non-obvious behavior by mapping each kind to its jobId source (designId for generation, designSystemId for design_system_import). It omits what a terminal result or failure looks like, which matters for a polling tool.

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?

Front-loaded with the actionable instruction then the kind taxonomy in one dense sentence; almost no waste. The kind list is semicolon-packed and readable, though a structured list would scan faster.

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?

With no output schema, the description should say what a completed versus in-progress poll returns; it says only 'until it is done' without status values or failure semantics. Everything else an agent needs to call it correctly is present.

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 100%, so baseline is 3; the description earns above baseline by explaining what each enum value actually covers (agent = design runs, React edits, videos; export = video files) rather than just repeating the enum. It does not describe the free-form 'params' object beyond deferring to guide().

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 concrete verb and resource: 'Check a job until it is done', plus a polling cadence. That is far more specific than a name restatement, but it never names a sibling (e.g. stop_job) to contrast against, so differentiation is only implied by the kind taxonomy.

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?

Gives clear operating context: call this repeatedly after a starting call and poll every 5 to 10 seconds. It does not state when-not to use it or how to distinguish a terminal failure from continued progress, and it does not point to stop_job as the alternative for cancelling.

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