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

With no annotations the description carries the full burden, and it delivers real behavioral facts: a hard 50-row cap per call, offset-based pagination, an accompanying total count, a CSV download URL, and the precondition that the job must be finished. It does not cover auth requirements or behavior/errors for unfinished jobs, keeping it below a 5.

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?

Two tight sentences, front-loaded with the scope and payload, followed by a directive on how to present results. Every clause earns its place and nothing is redundant.

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?

There is no output schema, and the description compensates by naming the return contents (sample rows, total count, CSV URL) and the pagination contract. Combined with the partial parameter coverage, an agent has enough to call it correctly, though the unfinished-job case is unaddressed.

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 0%, so the description must compensate. It clarifies limit (max 50 per call) and offset (pagination), which are the non-obvious two of three parameters; job_id is only implicitly explained via "a finished job's rows." Adequate but not complete given the zero coverage baseline.

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 gives a specific verb and resource ("Preview of a finished job's rows") and enumerates the payload (rows + total count + CSV URL), so an agent can tell it apart from metadata-oriented siblings like get_job and list_jobs. It falls short of a 5 only because it never explicitly names those siblings or the distinction.

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?

It states the operating condition (finished jobs), the pagination mechanism, and prescriptive usage — "show a sample, give the link" rather than dumping rows. What's missing is an explicit contrast with sibling tools or a statement of when this preview is the wrong choice.

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