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

Adds real behavior beyond the annotations: one credit per successful file, a per-plan row ceiling, the `batch_row_limit` error code with the plan's own number, and the four terminal states to poll for. Annotations already cover the safety profile (non-destructive, idempotent, open-world), so this is strong additional context, though auth requirements and what a partial run means for already-spent credits are left unstated.

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?

Four tight sentences, front-loaded with the core behavior and then escalating to limits, cost, and the polling loop. No filler and every sentence carries distinct operational 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?

With no output schema, the description usefully enumerates the terminal states (complete, partial, failed, cancelled) an agent must poll for, so the outcome space is covered. It stops short of describing the status payload or what a partial result contains, which is a minor gap for a job-starting tool.

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 80%, so the schema already documents rows, version, template_id, and idempotency_key. The description adds the 200-row ceiling and credit cost but says nothing about format choices, version pinning, or idempotency-key reuse beyond what the schema already states.

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 (render) plus resource (one saved template version) and the cardinality rule (once per data row, up to 200 rows), which cleanly separates it from the single-item `render` sibling. An agent knows exactly what work this starts.

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?

Tells the agent to poll get_status until the batch reaches a terminal state, which is the key follow-up guidance for a long-running job. It does not explicitly contrast with `render` or `retry_batch`, but the batch-vs-single distinction is implied by the row semantics.

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