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

Annotations only declare the generic write/idempotency flags; the description adds the operationally critical behavior: each call blocks up to 90 s and returns either "running" (with jobId and frame progress) or "done", with a documented re-invocation pattern using jobId. It also discloses cost (6 s of monthly allowance per GPU second) and the per-workspace concurrency limit, none of which the annotations convey.

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 core action and timing, then preconditions, then polling, then billing — a logical order with no filler. It is dense, semicolon-chained prose in a single block, which makes the polling and billing rules easy to skim past, but every sentence carries information.

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?

An output schema exists, so return shape need not be re-explained, yet the description still covers the states an agent must branch on, the wait limit, the cost model, and the concurrency constraint. For a paid, long-running, asynchronous-triggering render job, nothing essential to calling it correctly is missing.

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 parameter meaning is already largely supplied; the description still adds value by tying projectDir to a validation prerequisite and confirming the output default location. The jobId polling semantics are covered in the prose but only lightly restated for the resume case.

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 artifact ("Render the final MP4 of a faceless-production HyperFrames project ... on a GPU"), naming the exact input folder and output path. It immediately distinguishes itself from the CPU render done in the workspace, which is the closest sibling behavior (workspace_exec).

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?

Explains the preconditions (projectDir must follow cf-prep and hyperframes check passing) and points to get_workflow_instructions with the faceless-production workflow as the starting point. It also contrasts the alternative (CPU render in the workspace) and states the concurrency rule (one render per workspace), leaving little to inference.

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